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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 19048
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript code related to window display and navigation structures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    326
    +0.12
    0.6%
    153
    +0.11
    0.5%
    497
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.12
    0.04
    507
    +0.11
    0.04
    326
    +0.10
    0.03
    Negative Logits
    itton
    -0.70
     Tas
    -0.66
    actor
    -0.65
    andise
    -0.61
    ignore
    -0.60
     props
    -0.60
     Tyrann
    -0.59
     Jinn
    -0.59
     unpre
    -0.59
     Fraz
    -0.58
    POSITIVE LOGITS
    192
    1.25
    eenth
    1.23
    een
    1.22
    ecause
    1.03
    989
    0.99
    98
    0.91
    57
    0.90
    90
    0.89
    987
    0.89
    swick
    0.86
    Activations Density 0.076%

    No Known Activations