© 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. 18925
    Prev
    Next
    INDEX
    Explanations

    city-level or state-level directives or policies

    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
    502
    +0.12
    0.5%
    392
    +0.10
    0.5%
    91
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.12
    0.02
    104
    +0.10
    0.01
    502
    +0.10
    0.01
    Negative Logits
     Raz
    -0.66
     Ban
    -0.64
    unin
    -0.63
     OC
    -0.63
     tum
    -0.63
     resc
    -0.61
     uber
    -0.61
     surgical
    -0.61
     Trin
    -0.60
     Pyro
    -0.59
    POSITIVE LOGITS
    ;
    1.44
    .;
    1.38
    ;"
    1.29
    ;}
    1.21
    %;
    1.15
    ';
    1.08
     ;
    1.06
    âĢ¢
    1.06
    '';
    1.04
    ;;
    1.03
    Activations Density 0.040%

    No Known Activations