© 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. 2966
    Prev
    Next
    INDEX
    Explanations

    items or concepts related to specific in-game motifs or items

    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
    464
    +0.10
    0.5%
    294
    +0.09
    0.4%
    68
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.10
    0.04
    588
    +0.09
    0.06
    232
    +0.09
    0.06
    Negative Logits
     Guer
    -0.75
     contempor
    -0.73
     confer
    -0.68
    terday
    -0.67
     Caesar
    -0.66
     Pin
    -0.65
     Rein
    -0.63
     VICE
    -0.62
     decriminal
    -0.60
    CU
    -0.60
    POSITIVE LOGITS
    asses
    1.24
    lems
    1.09
    ples
    1.09
    keys
    1.06
    ees
    1.04
    ables
    1.03
    acters
    1.02
    ivities
    1.02
    ids
    1.01
    bies
    1.01
    Activations Density 1.237%

    No Known Activations