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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23651
    Prev
    Next
    INDEX
    Explanations

    references to historical figures or events related to the Chandela dynasty

    oai_token-act-pair · gpt-4o-miniTriggered 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
    393
    +0.12
    0.5%
    518
    +0.10
    0.5%
    556
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.12
    0.05
    556
    +0.10
    0.05
    668
    +0.10
    0.04
    Negative Logits
    efully
    -0.76
    Fla
    -0.67
    reason
    -0.65
    erial
    -0.64
    IRT
    -0.64
    STON
    -0.62
     Pew
    -0.60
    progress
    -0.59
    past
    -0.59
    loads
    -0.59
    POSITIVE LOGITS
    phia
    0.92
    tsy
    0.83
     herself
    0.82
     himself
    0.80
     Himself
    0.80
    's
    0.79
    Sov
    0.79
     Productions
    0.77
    ensis
    0.74
    ã쮿
    0.74
    Activations Density 0.208%

    No Known Activations