© 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. 24008
    Prev
    Next
    INDEX
    Explanations

    phrases related to strength, value, and importance in various contexts

    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
    116
    +0.13
    0.6%
    10
    +0.12
    0.6%
    397
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    513
    +0.13
    0.02
    327
    +0.12
    0.02
    194
    +0.11
    0.02
    Negative Logits
    berra
    -0.73
    ength
    -0.72
     resolutions
    -0.68
    idth
    -0.68
    ylum
    -0.67
    !/
    -0.64
    ysis
    -0.63
    rev
    -0.63
    aido
    -0.61
     consisted
    -0.60
    POSITIVE LOGITS
     unsu
    0.95
     uniquely
    0.86
     formidable
    0.85
     ripe
    0.84
    inently
    0.81
     unique
    0.80
     unbeat
    0.77
     versatile
    0.76
     attractive
    0.76
     target
    0.74
    Activations Density 0.103%

    No Known Activations