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. 21757
    Prev
    Next
    INDEX
    Explanations

    mentions of specific people and their actions or characteristics

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    92
    +0.13
    0.6%
    362
    +0.12
    0.6%
    8
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.07
    92
    +0.12
    0.06
    15
    +0.10
    0.06
    Negative Logits
    ibaba
    -0.85
    llular
    -0.77
    umblr
    -0.72
    ãĥ´ãĤ¡
    -0.68
    igslist
    -0.67
    ĸļ
    -0.64
    Internet
    -0.64
    tin
    -0.63
    Stre
    -0.63
    ersed
    -0.63
    POSITIVE LOGITS
     colleague
    1.39
     own
    1.30
     colleagues
    1.29
     constituents
    1.13
     predecessors
    1.11
     clients
    1.09
     predecessor
    1.09
     nephew
    1.08
     daughter
    1.06
     son
    1.05
    Activations Density 0.232%

    No Known Activations