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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 1638
    Prev
    Next
    INDEX
    Explanations

    references to events, locations, and services offering free admission or services

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    119
    +0.11
    0.5%
    222
    +0.11
    0.5%
    188
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.11
    0.04
    222
    +0.11
    0.04
    119
    +0.11
    0.03
    Negative Logits
    older
    -0.82
    ENTION
    -0.70
    need
    -0.68
    igham
    -0.68
     Nightmares
    -0.68
    amel
    -0.67
    itect
    -0.67
    Dialogue
    -0.65
    itta
    -0.65
    ulous
    -0.65
    POSITIVE LOGITS
    bies
    1.44
    bie
    1.25
    zers
    1.03
    zing
    1.01
    zes
    0.99
     roam
    0.99
     downloadable
    0.93
    ze
    0.81
     download
    0.81
    credit
    0.80
    Activations Density 0.031%

    No Known Activations