© 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. 24538
    Prev
    Next
    INDEX
    Explanations

    specific names and titles, especially in cultural or historical contexts

    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
    480
    +0.37
    1.9%
    373
    +0.14
    0.7%
    674
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.37
    0.09
    659
    +0.14
    0.09
    314
    +0.12
    -0.01
    Negative Logits
     respectively
    -0.88
    $.
    -0.76
     thereof
    -0.74
     thereto
    -0.66
    }.
    -0.65
     predetermined
    -0.64
     rece
    -0.62
     therein
    -0.61
    )).
    -0.61
    ]."
    -0.60
    POSITIVE LOGITS
     Profile
    0.81
     âĵĺ
    0.76
    !:
    0.74
    ':
    0.67
    udos
    0.63
     Edit
    0.60
     Releases
    0.60
    iasis
    0.59
     Aging
    0.57
     Facts
    0.56
    Activations Density 0.668%

    No Known Activations