© 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. 2999
    Prev
    Next
    INDEX
    Explanations

    words related to deals, agreements, or contracts

    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
    278
    +0.10
    0.4%
    92
    +0.10
    0.4%
    18
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.10
    0.09
    278
    +0.10
    0.08
    100
    +0.09
    0.08
    Negative Logits
    ires
    -0.77
    ocracy
    -0.69
    ETS
    -0.64
     Pony
    -0.63
    ocratic
    -0.61
    efer
    -0.60
    onday
    -0.60
    eval
    -0.60
     Wast
    -0.59
    estro
    -0.59
    POSITIVE LOGITS
    chard
    1.57
    acles
    1.50
    acle
    1.48
    Else
    1.43
    ifice
    1.39
    nam
    1.38
    chid
    1.37
    acular
    1.31
     alternatively
    1.26
     else
    1.20
    Activations Density 0.485%

    No Known Activations