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. 26393
    Prev
    Next
    INDEX
    Explanations

    terms related to body parts and their modifications or alterations

    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
    737
    +0.10
    0.4%
    40
    +0.09
    0.4%
    435
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.10
    0.03
    435
    +0.09
    0.03
    475
    +0.09
    0.03
    Negative Logits
     Rooms
    -0.83
     attendance
    -0.75
     sanity
    -0.74
     accommodations
    -0.72
    EMS
    -0.71
     rooms
    -0.70
     absentee
    -0.69
     workload
    -0.69
    quickShipAvailable
    -0.68
     Atmosp
    -0.68
    POSITIVE LOGITS
     protr
    1.30
     diameter
    0.97
    bone
    0.96
    tip
    0.96
     shaped
    0.94
     adorned
    0.93
     tipped
    0.93
    bill
    0.93
     pier
    0.92
    prints
    0.92
    Activations Density 0.084%

    No Known Activations