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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11728
    Prev
    Next
    INDEX
    Explanations

    phrases related to protests and demonstrations

    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
    644
    +0.12
    0.6%
    275
    +0.11
    0.5%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.01
    215
    +0.11
    0.01
    505
    +0.11
    0.01
    Negative Logits
    士
    -0.72
     Tycoon
    -0.72
    Reviewed
    -0.71
    amate
    -0.71
    nesota
    -0.71
    éĸ
    -0.67
    neau
    -0.67
    iciary
    -0.65
    itaire
    -0.65
    ATES
    -0.64
    POSITIVE LOGITS
     chanting
    1.20
     chanted
    1.12
     chants
    1.10
     slogans
    1.10
     chant
    1.08
     louder
    1.02
     aloud
    0.95
     loudly
    0.88
     sung
    0.78
     chorus
    0.77
    Activations Density 0.023%

    No Known Activations