© 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. 13286
    Prev
    Next
    INDEX
    Explanations

    information related to educational institutions and financial matters

    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
    481
    +0.15
    0.7%
    122
    +0.11
    0.5%
    177
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.15
    0.04
    149
    +0.11
    0.03
    73
    +0.10
    0.04
    Negative Logits
    lique
    -0.80
    xual
    -0.78
    erent
    -0.76
    ĪĴ
    -0.75
    omething
    -0.72
    ¬¼
    -0.70
    avez
    -0.69
    ses
    -0.69
    THING
    -0.69
    ²¾
    -0.68
    POSITIVE LOGITS
     surpass
    1.05
    behind
    0.99
     boasting
    0.90
     ranking
    0.88
     excluding
    0.86
    Ranked
    0.85
     according
    0.81
     ranked
    0.81
     surpassed
    0.81
     averaging
    0.78
    Activations Density 0.326%

    No Known Activations