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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 26054
    Prev
    Next
    INDEX
    Explanations

    references to human rights organizations and related terminology

    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
    435
    +0.12
    0.5%
    566
    +0.10
    0.4%
    218
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    435
    +0.12
    0.01
    734
    +0.10
    0.01
    659
    +0.09
    0.01
    Negative Logits
    cart
    -0.79
    coni
    -0.77
    âĸ¬
    -0.73
     Albion
    -0.72
    lihood
    -0.69
     ç¥ŀ
    -0.66
    âĶĢâĶĢ
    -0.65
     Homo
    -0.64
    sov
    -0.64
     Mandela
    -0.63
    POSITIVE LOGITS
    DP
    0.99
    RR
    0.96
    Ds
    0.93
    RI
    0.92
    RP
    0.92
    DK
    0.92
    adish
    0.89
    RD
    0.89
    HR
    0.88
    TF
    0.87
    Activations Density 0.005%

    No Known Activations