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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9086
    Prev
    Next
    INDEX
    Explanations

    references to actions, events, and discussions in a narrative context

    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
    314
    +0.18
    0.8%
    373
    +0.14
    0.6%
    55
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.18
    0.07
    102
    +0.14
    0.06
    580
    +0.12
    0.04
    Negative Logits
     Vers
    -0.70
     SPD
    -0.70
     juven
    -0.66
     dismant
    -0.66
     pursu
    -0.63
     millenn
    -0.63
     Techn
    -0.61
     predicate
    -0.61
     stag
    -0.61
     traged
    -0.61
    POSITIVE LOGITS
    senal
    0.99
    rael
    0.98
    tics
    0.96
    Ĥİ
    0.95
     guiActiveUnfocused
    0.86
    ws
    0.84
    abella
    0.83
    omorphic
    0.83
    wolves
    0.83
    sis
    0.82
    Activations Density 0.366%

    No Known Activations