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. 26142
    Prev
    Next
    INDEX
    Explanations

    references to the neck in various contexts

    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
    285
    +0.13
    0.6%
    587
    +0.11
    0.5%
    563
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.13
    0.01
    678
    +0.11
    0.01
    370
    +0.10
    0.01
    Negative Logits
    ========
    -0.71
     Suc
    -0.67
    Magikarp
    -0.65
    ============
    -0.64
    ãĥĩ
    -0.63
     Outbreak
    -0.63
    urity
    -0.62
     Atmosp
    -0.62
     Sigma
    -0.62
    âĦ¢:
    -0.62
    POSITIVE LOGITS
    lace
    1.59
    tie
    1.45
    beard
    1.27
    line
    1.16
    bones
    1.14
    lines
    1.12
    bone
    1.06
    breaker
    0.92
    breakers
    0.91
    guards
    0.90
    Activations Density 0.007%

    No Known Activations