© 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 EvalsExportsinterp-engineNEWAPI 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. 24407
    Prev
    Next
    INDEX
    Explanations

    mentions of academic articles and reports

    oai_token-act-pair · gpt-4o-miniTriggered 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
    +0.12
    0.5%
    475
    +0.11
    0.5%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.12
    0.05
    430
    +0.11
    0.06
    452
    +0.10
    0.04
    Negative Logits
     accommodation
    -0.75
    tsy
    -0.72
     toast
    -0.68
    ah
    -0.63
    dom
    -0.63
    eering
    -0.63
     drain
    -0.61
    care
    -0.60
     hers
    -0.59
    "},"
    -0.59
    POSITIVE LOGITS
     titled
    1.14
     headlined
    1.09
     published
    1.01
     excerpts
    0.99
    vertisement
    0.99
     reprinted
    0.96
    published
    0.92
     authored
    0.91
     excerpt
    0.89
     entitled
    0.89
    Activations Density 0.335%

    No Known Activations