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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12204
    Prev
    Next
    INDEX
    Explanations

    occurrences of the sequence "LL" which appears in various contexts throughout the text

    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
    373
    +0.10
    0.4%
    742
    +0.10
    0.4%
    11
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.10
    0.01
    373
    +0.10
    -0.00
    11
    +0.09
    0.01
    Negative Logits
    qua
    -0.73
    hered
    -0.67
    lde
    -0.65
    itutes
    -0.63
    cean
    -0.63
    emaker
    -0.61
    elist
    -0.60
    cade
    -0.60
    chnology
    -0.60
    ãĥĥ
    -0.59
    POSITIVE LOGITS
    INGTON
    1.24
    iard
    1.07
    uminati
    1.04
    ibrary
    1.02
    oyd
    0.98
    ounge
    0.96
    NESS
    0.96
    ION
    0.95
    ateral
    0.94
    owship
    0.92
    Activations Density 0.004%

    No Known Activations