© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 41491
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to buildings or establishments, particularly those named "House."

    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
    152
    +0.12
    0.5%
    496
    +0.11
    0.5%
    76
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    531
    +0.12
    0.03
    152
    +0.11
    0.03
    76
    +0.11
    0.02
    Negative Logits
    onal
    -0.75
    ï¸ı
    -0.72
    inez
    -0.72
    ially
    -0.69
    istical
    -0.69
    oshop
    -0.69
    ilitary
    -0.68
    aneously
    -0.68
    istically
    -0.68
    ICAL
    -0.62
    POSITIVE LOGITS
    wives
    1.54
    wife
    1.41
    keeping
    1.27
    warming
    1.00
    holders
    0.98
    keeper
    0.96
    hold
    0.95
    holder
    0.93
    plant
    0.92
    keepers
    0.92
    Activations Density 0.020%

    No Known Activations