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. 43179
    Prev
    Next
    INDEX
    Explanations

    phrases related to variations or differences in 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
    160
    +0.15
    0.7%
    99
    +0.10
    0.5%
    109
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.15
    0.01
    271
    +0.10
    0.01
    539
    +0.10
    0.01
    Negative Logits
    Ķ
    -0.74
    ãĥĥãĥī
    -0.69
    lehem
    -0.64
    ת
    -0.63
     shoulders
    -0.61
     peanuts
    -0.60
    ij
    -0.60
    ¯¯¯¯
    -0.59
    mega
    -0.59
    ãĥİ
    -0.59
    POSITIVE LOGITS
    arily
    1.05
    aution
    1.00
     thereof
    0.91
    yip
    0.84
    dayName
    0.84
    iveness
    0.83
    arios
    0.82
    iator
    0.81
    ials
    0.81
    iations
    0.77
    Activations Density 0.016%

    No Known Activations