© 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. 41497
    Prev
    Next
    INDEX
    Explanations

    words related to necessities and requirements

    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
    46
    +0.12
    0.5%
    60
    +0.09
    0.4%
    541
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    46
    +0.12
    0.02
    657
    +0.09
    0.02
    60
    +0.09
    0.01
    Negative Logits
    iple
    -0.75
    gdala
    -0.71
    pret
    -0.70
    blogspot
    -0.69
    etsy
    -0.69
    Ń·
    -0.67
    soType
    -0.66
    deck
    -0.66
    hov
    -0.66
    wordpress
    -0.66
    POSITIVE LOGITS
     to
    0.85
     for
    0.76
     requisite
    0.70
     thereto
    0.69
     manpower
    0.68
    ioned
    0.66
     necessary
    0.63
     servicing
    0.63
     conducive
    0.63
     signatures
    0.61
    Activations Density 0.025%

    No Known Activations