© 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. 6567
    Prev
    Next
    INDEX
    Explanations

    technical code-related expressions and formats

    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
    481
    +0.59
    6.7%
    480
    +0.45
    5.1%
    266
    +0.08
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.59
    0.01
    266
    +0.45
    0.18
    481
    +0.08
    0.18
    Negative Logits
    senal
    -0.28
    NW
    -0.25
     Cosponsors
    -0.24
    SpaceEngineers
    -0.24
    PLA
    -0.24
     USAF
    -0.23
     Devi
    -0.23
    ©¶æ
    -0.23
     Canaver
    -0.23
    trump
    -0.22
    POSITIVE LOGITS
    ettle
    0.21
    joice
    0.20
     cores
    0.20
    <
    0.20
     rid
    0.20
    ertain
    0.19
     sip
    0.19
     instead
    0.19
     comb
    0.19
    ines
    0.19
    Activations Density 4.530%

    No Known Activations