© 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 3072
    9. 8-RES_FS3072-JB
    11. 3064
    Prev
    Next
    INDEX
    Explanations

    mentions of names in a specific context or event

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    227
    +0.10
    0.5%
    462
    +0.10
    0.5%
    614
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.10
    659
    +0.10
    0.07
    227
    +0.10
    0.05
    Negative Logits
     WiFi
    -0.77
    å¸
    -0.72
     stew
    -0.67
    Stew
    -0.65
    LOS
    -0.64
     WR
    -0.63
     Stellar
    -0.63
    VL
    -0.62
    WOR
    -0.62
     stre
    -0.62
    POSITIVE LOGITS
    aq
    1.06
    amate
    1.04
    ab
    1.01
    adh
    1.00
    Äģ
    0.99
    as
    0.98
    am
    0.98
    af
    0.97
    ac
    0.97
    aan
    0.97
    Activations Density 0.972%

    No Known Activations