Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 41379
    Prev
    Next
    INDEX
    Explanations

    the possessive form indicating ownership or association, specifically using the contraction "’s"

    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
    393
    +0.15
    0.7%
    608
    +0.14
    0.6%
    362
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    550
    +0.15
    0.02
    199
    +0.14
    0.02
    664
    +0.12
    0.01
    Negative Logits
    wright
    -0.83
    athy
    -0.82
    ships
    -0.75
    este
    -0.74
    JR
    -0.73
    VO
    -0.72
    conom
    -0.72
    xxx
    -0.72
    VPN
    -0.71
    hari
    -0.70
    POSITIVE LOGITS
     edition
    1.15
     iteration
    0.98
     installment
    0.94
     inaugural
    0.94
     anniversary
    0.93
     hottest
    0.88
     winner
    0.88
     winners
    0.86
     editions
    0.85
     incarnation
    0.84
    Activations Density 0.018%

    No Known Activations