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. 712
    Prev
    Next
    INDEX
    Explanations

    words related to exclusivity or elite status

    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
    742
    +0.14
    0.6%
    153
    +0.12
    0.5%
    119
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    742
    +0.14
    0.02
    153
    +0.12
    0.02
    21
    +0.11
    0.02
    Negative Logits
     Inspection
    -0.66
    nant
    -0.65
     Continued
    -0.63
    itives
    -0.63
    LESS
    -0.62
    ãĥ´ãĤ¡
    -0.61
    orial
    -0.60
     Accountability
    -0.60
    NEY
    -0.60
    xit
    -0.60
    POSITIVE LOGITS
    izabeth
    1.19
    ibrary
    1.18
    usive
    1.12
    iquid
    1.09
    ixir
    1.08
    abor
    0.98
    uding
    0.94
    igible
    0.93
    uded
    0.93
    ipt
    0.91
    Activations Density 0.013%

    No Known Activations