© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7961
    Prev
    Next
    INDEX
    Explanations

    movie-related terms and titles

    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
    7
    +0.12
    0.5%
    84
    +0.11
    0.5%
    620
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    620
    +0.12
    0.03
    690
    +0.11
    0.04
    749
    +0.10
    0.04
    Negative Logits
     sensing
    -0.76
     Upper
    -0.72
    upper
    -0.71
    bolt
    -0.71
    zbek
    -0.69
    arent
    -0.68
    ebus
    -0.68
    ERC
    -0.67
    erous
    -0.66
    claw
    -0.64
    POSITIVE LOGITS
     genres
    1.21
     genre
    1.18
     sequels
    1.06
     starring
    0.98
    genre
    0.97
     premiered
    0.93
     anthology
    0.93
     cinematic
    0.92
     narrated
    0.90
     movies
    0.89
    Activations Density 0.653%

    No Known Activations