© 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. 19329
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Dell"

    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
    582
    +0.13
    0.6%
    31
    +0.12
    0.6%
    683
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    582
    +0.13
    0.02
    31
    +0.12
    0.02
    284
    +0.11
    0.02
    Negative Logits
     exha
    -0.71
    ItemTracker
    -0.64
     citiz
    -0.64
    dayName
    -0.63
    Reply
    -0.63
    displayText
    -0.63
     guiActiveUn
    -0.62
    REM
    -0.61
     trave
    -0.61
     arous
    -0.60
    POSITIVE LOGITS
    owship
    1.37
    iott
    1.11
    inger
    1.06
     Beckham
    1.02
    uminati
    1.02
    esy
    0.98
    ows
    0.97
    agic
    0.96
    igent
    0.95
    wagen
    0.93
    Activations Density 0.022%

    No Known Activations