© 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. 12795
    Prev
    Next
    INDEX
    Explanations

    names of individuals or 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
    659
    +0.12
    0.6%
    126
    +0.11
    0.5%
    636
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.09
    232
    +0.11
    0.05
    511
    +0.10
    0.05
    Negative Logits
    VALUE
    -0.82
    âĶĢâĶĢ
    -0.80
    EVA
    -0.78
    IUM
    -0.75
    URA
    -0.74
    ãĥŁ
    -0.73
    romeda
    -0.73
    REDACTED
    -0.70
    ··
    -0.70
    incial
    -0.69
    POSITIVE LOGITS
    iggs
    0.83
    isner
    0.82
    verson
    0.78
    ogg
    0.77
    houn
    0.75
    iffin
    0.74
     McL
    0.73
     McC
    0.71
    antz
    0.71
    sworth
    0.70
    Activations Density 0.162%

    No Known Activations