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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19874
    Prev
    Next
    INDEX
    Explanations

    addresses or locations

    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
    484
    +0.12
    0.5%
    94
    +0.10
    0.5%
    532
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.12
    0.02
    232
    +0.10
    0.02
    41
    +0.10
    0.02
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.74
    WARE
    -0.66
     AMERICA
    -0.65
    requires
    -0.63
    rers
    -0.63
     Contra
    -0.62
     Relief
    -0.62
    NESS
    -0.62
     stag
    -0.62
    âĶĢâĶĢâĶĢâĶĢ
    -0.61
    POSITIVE LOGITS
    atton
    1.42
    acket
    1.30
    anches
    1.28
    onson
    1.22
    ackets
    1.22
    anson
    1.19
    anca
    1.13
    idget
    1.13
    ains
    1.12
    addock
    1.12
    Activations Density 0.014%

    No Known Activations