© 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. 22379
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inclusion or reference to a group

    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
    409
    +0.10
    0.5%
    89
    +0.09
    0.4%
    756
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    313
    +0.10
    0.02
    409
    +0.09
    0.02
    661
    +0.08
    0.01
    Negative Logits
    irez
    -0.72
    adian
    -0.71
    ifix
    -0.68
    idia
    -0.63
    agos
    -0.61
    bane
    -0.61
    nery
    -0.60
    ysc
    -0.58
    iltr
    -0.57
    ulas
    -0.57
    POSITIVE LOGITS
    st
    0.80
    IJ
    0.79
    Īè
    0.71
     others
    0.70
    among
    0.70
     whom
    0.70
    SPONSORED
    0.68
    ī
    0.66
     notable
    0.66
    ĪĴ
    0.65
    Activations Density 0.017%

    No Known Activations