© 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. 7429
    Prev
    Next
    INDEX
    Explanations

    terms related to political and economic issues, likely focusing on references to government interventions and ideological leanings

    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
    635
    +0.12
    0.6%
    538
    +0.12
    0.5%
    92
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.06
    608
    +0.12
    0.06
    635
    +0.10
    0.04
    Negative Logits
    $$
    -0.75
     Annotations
    -0.74
     deserve
    -0.71
    etimes
    -0.69
    icious
    -0.69
    brance
    -0.66
     Thousands
    -0.65
     Parenthood
    -0.63
    flies
    -0.63
     importantly
    -0.61
    POSITIVE LOGITS
     minimalist
    1.08
     simplistic
    1.02
     pragmatic
    1.01
    traditional
    0.99
     neutrality
    0.98
     cautious
    0.97
     narrower
    0.97
     simpler
    0.96
     strict
    0.93
     softer
    0.90
    Activations Density 0.394%

    No Known Activations