© 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 3072
    9. 8-RES_FS3072-JB
    11. 2963
    Prev
    Next
    INDEX
    Explanations

    descriptions of personal experiences and observations, possibly related to retail shopping or personal interactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    751
    +0.11
    0.5%
    685
    +0.10
    0.5%
    84
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    614
    +0.11
    0.07
    526
    +0.10
    -0.01
    685
    +0.10
    0.04
    Negative Logits
    itudinal
    -0.71
    ATIVE
    -0.67
    andi
    -0.66
    pmwiki
    -0.65
     culminating
    -0.65
     facets
    -0.64
     Immunity
    -0.64
    iveness
    -0.63
     Factors
    -0.62
     procedural
    -0.61
    POSITIVE LOGITS
     vending
    1.07
     circulation
    1.04
     sale
    0.98
     shelves
    0.91
     supermarkets
    0.90
    pload
    0.87
     disposal
    0.86
    washer
    0.86
     purchase
    0.85
     shops
    0.85
    Activations Density 2.572%

    No Known Activations