© 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 49152
    9. 8-RES_FS49152-JB
    11. 37409
    Prev
    Next
    INDEX
    Explanations

    descriptions and mentions of legal actions and controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    480
    +0.40
    2.2%
    464
    +0.19
    1.0%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.40
    0.01
    266
    +0.19
    0.10
    362
    +0.10
    0.08
    Negative Logits
    -)
    -0.67
    =-=-
    -0.60
     rul
    -0.59
     *)
    -0.55
    ngth
    -0.54
     þ
    -0.53
    olicy
    -0.53
    iple
    -0.52
    !]
    -0.52
    ecause
    -0.51
    POSITIVE LOGITS
    realDonaldTrump
    0.50
     graphene
    0.50
     Tibetan
    0.49
     Glacier
    0.49
     environmentally
    0.48
     vagina
    0.48
    DCS
    0.47
     2020
    0.46
    oplan
    0.45
     Bashar
    0.45
    Activations Density 1.515%

    No Known Activations