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 24576
    5. 8-RES_FS24576-JB
    6. 23149
    Prev
    Next
    INDEX
    Explanations

    references to specific fields or categories related to a subject

    oai_token-act-pair · gpt-4o-miniTriggered 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
    288
    +0.13
    0.6%
    29
    +0.11
    0.5%
    109
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.13
    0.03
    288
    +0.11
    0.03
    99
    +0.10
    0.02
    Negative Logits
    bian
    -0.74
    ï¸
    -0.72
    éĹĺ
    -0.72
    ILLE
    -0.71
    Priv
    -0.67
    ilyn
    -0.64
     Fas
    -0.64
    atron
    -0.63
    uyomi
    -0.62
    mins
    -0.62
    POSITIVE LOGITS
    fields
    0.87
    field
    0.84
    spring
    0.83
    plane
    0.82
    sheet
    0.82
    grass
    0.81
    finder
    0.81
     sob
    0.77
    quarters
    0.75
    planes
    0.74
    Activations Density 0.036%

    No Known Activations