© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 14271
    Prev
    Next
    INDEX
    Explanations

    terms related to traits, characteristics, and qualities in the context of hiring, personalities, and attributes of different entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    540
    +0.13
    0.6%
    255
    +0.11
    0.5%
    575
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.13
    0.03
    724
    +0.11
    0.03
    255
    +0.11
    0.02
    Negative Logits
    endar
    -0.86
    source
    -0.81
    NAS
    -0.74
    endars
    -0.73
    DERR
    -0.73
    sites
    -0.71
    vernment
    -0.70
    hand
    -0.69
    foreseen
    -0.69
    aii
    -0.65
    POSITIVE LOGITS
     traits
    1.26
     characteristics
    1.03
     trait
    1.02
     qualities
    0.99
     predis
    0.92
     characteristic
    0.88
    hered
    0.86
     weaknesses
    0.85
    istics
    0.83
     attributes
    0.80
    Activations Density 0.041%

    No Known Activations