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. 43381
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Holt."

    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
    273
    +0.10
    0.5%
    359
    +0.10
    0.5%
    203
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.10
    0.01
    419
    +0.10
    0.01
    66
    +0.10
    0.01
    Negative Logits
    EED
    -0.80
    ISSION
    -0.73
    isable
    -0.70
     quo
    -0.67
    IENT
    -0.66
    pires
    -0.65
    AFTA
    -0.64
    acement
    -0.64
     distingu
    -0.60
    ceed
    -0.59
    POSITIVE LOGITS
    zman
    1.44
    mann
    1.01
    kamp
    1.01
    bys
    0.92
    bard
    0.90
    zeb
    0.86
    zer
    0.86
    stad
    0.86
    ter
    0.85
    acan
    0.85
    Activations Density 0.005%

    No Known Activations