© 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 49152
    9. 8-RES_FS49152-JB
    11. 37040
    Prev
    Next
    INDEX
    Explanations

    references to roles and performances in acting or film contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    540
    +0.13
    0.6%
    160
    +0.12
    0.5%
    360
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.13
    0.03
    708
    +0.12
    0.02
    78
    +0.11
    0.01
    Negative Logits
    £ı
    -0.77
    vironment
    -0.69
    hig
    -0.68
    pex
    -0.67
     enrichment
    -0.67
    Statistics
    -0.67
    imb
    -0.67
    TPPStreamerBot
    -0.63
    foundation
    -0.63
    ruciating
    -0.62
    POSITIVE LOGITS
     actress
    0.96
     portraying
    0.87
     actor
    0.85
     portrayal
    0.83
     roles
    0.83
     starring
    0.83
     portray
    0.81
     Actress
    0.80
     actresses
    0.80
    wright
    0.80
    Activations Density 0.029%

    No Known Activations