Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 6144
    5. 8-RES_FS6144-JB
    6. 5540
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms and trends

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    756
    +0.12
    0.5%
    596
    +0.10
    0.4%
    228
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.12
    0.06
    607
    +0.10
    0.06
    756
    +0.09
    -0.04
    Negative Logits
     blasp
    -0.90
     oath
    -0.88
     tresp
    -0.88
    wiki
    -0.84
     pedoph
    -0.83
     godd
    -0.81
     Scientology
    -0.80
     indoctr
    -0.78
     fucking
    -0.74
     rapist
    -0.74
    POSITIVE LOGITS
     forecast
    1.34
     forecasts
    1.33
     recession
    1.30
    flation
    1.27
     bullish
    1.25
     slowdown
    1.23
     forecasting
    1.20
     inflation
    1.16
     GDP
    1.16
     unemployment
    1.14
    Activations Density 2.357%

    No Known Activations