© 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 EvalsExportsAPI 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. 12446
    Prev
    Next
    INDEX
    Explanations

    phrases related to advising someone to take a specific action or make a decision

    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
    354
    +0.14
    0.7%
    377
    +0.13
    0.6%
    437
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.14
    0.07
    377
    +0.13
    0.07
    437
    +0.10
    0.05
    Negative Logits
    ament
    -0.71
    creen
    -0.67
    ificent
    -0.66
    eers
    -0.65
    itionally
    -0.64
    ullah
    -0.64
    oret
    -0.60
     Horus
    -0.59
    icio
    -0.59
    ifully
    -0.59
    POSITIVE LOGITS
    vt
    1.12
    ggle
    1.05
    verning
    1.01
    lems
    1.01
     overboard
    0.95
    ALK
    0.91
     ahead
    0.86
     forth
    0.83
     unnoticed
    0.83
    ogly
    0.82
    Activations Density 0.095%

    No Known Activations