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 3072
    5. 8-RES_FS3072-JB
    6. 614
    Prev
    Next
    INDEX
    Explanations

    information related to legal cases and hearings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    314
    +0.15
    0.7%
    566
    +0.14
    0.7%
    344
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.15
    0.10
    344
    +0.14
    0.10
    552
    +0.13
    0.09
    Negative Logits
    PI
    -0.61
    âϦ
    -0.61
    bie
    -0.61
    bery
    -0.59
    owe
    -0.59
     Voters
    -0.58
    hammer
    -0.57
    hack
    -0.57
    etting
    -0.55
    uating
    -0.55
    POSITIVE LOGITS
     been
    1.35
     begun
    1.16
     undergone
    1.15
     gotten
    1.09
    iths
    1.09
     gone
    1.08
    been
    1.02
     previously
    0.96
     flown
    0.94
     taken
    0.91
    Activations Density 0.425%

    No Known Activations