© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 26526
    Prev
    Next
    INDEX
    Explanations

    the term "significant" and its variants in various contexts

    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
    316
    +0.13
    0.6%
    661
    +0.11
    0.5%
    579
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.13
    0.02
    661
    +0.11
    0.02
    579
    +0.11
    0.02
    Negative Logits
    ©¶æ
    -0.95
    nery
    -0.86
    elf
    -0.83
    iverpool
    -0.81
    creen
    -0.79
    IDES
    -0.73
    spr
    -0.73
    stein
    -0.72
    chers
    -0.72
    av
    -0.72
    POSITIVE LOGITS
     amounts
    1.10
    itarian
    1.06
     amount
    0.99
     portions
    0.93
     understatement
    0.90
     difference
    0.89
     improvement
    0.88
     imped
    0.88
     quantities
    0.88
     impact
    0.85
    Activations Density 0.023%

    No Known Activations