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. 23929
    Prev
    Next
    INDEX
    Explanations

    references to ownership or control, particularly in a social or legal context

    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
    247
    +0.11
    0.5%
    132
    +0.10
    0.5%
    484
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.11
    0.01
    132
    +0.10
    0.01
    592
    +0.10
    0.01
    Negative Logits
    ifiers
    -0.82
    ileaks
    -0.81
    ITION
    -0.81
     GOODMAN
    -0.78
    enhagen
    -0.76
    ifier
    -0.74
    IFIED
    -0.72
    ification
    -0.71
    DERR
    -0.70
    onna
    -0.69
    POSITIVE LOGITS
    holder
    0.78
    wreck
    0.74
    owners
    0.73
    llor
    0.72
    Hop
    0.72
     Yamato
    0.72
    ment
    0.70
    holders
    0.70
    hire
    0.69
    ments
    0.68
    Activations Density 0.012%

    No Known Activations