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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 45689
    Prev
    Next
    INDEX
    Explanations

    the phrase "under" followed by numbers, indicating statistical thresholds or limits

    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
    616
    +0.13
    0.6%
    363
    +0.10
    0.4%
    540
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.13
    0.03
    540
    +0.10
    0.02
    100
    +0.09
    0.02
    Negative Logits
     Edison
    -0.66
    iterranean
    -0.63
    aukee
    -0.62
     hereafter
    -0.61
     Hitman
    -0.60
     Maker
    -0.60
     Glob
    -0.59
     onward
    -0.59
     Retrieved
    -0.58
     Omega
    -0.58
    POSITIVE LOGITS
    stated
    1.22
    dogs
    1.17
    whelming
    1.16
    valued
    1.12
    priv
    1.11
    current
    1.10
    growth
    1.08
    performing
    1.07
    cutting
    1.06
    priced
    1.05
    Activations Density 0.021%

    No Known Activations