© 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. 23001
    Prev
    Next
    INDEX
    Explanations

    the pronoun "I" indicating personal perspective or involvement

    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
    718
    +0.15
    0.7%
    502
    +0.12
    0.6%
    377
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.15
    0.10
    718
    +0.12
    0.09
    93
    +0.12
    0.08
    Negative Logits
     substitutes
    -0.66
     selves
    -0.64
     totality
    -0.62
     membrane
    -0.59
     adhesive
    -0.59
     unfocusedRange
    -0.59
     souls
    -0.58
     tides
    -0.58
     markings
    -0.57
     bott
    -0.57
    POSITIVE LOGITS
    'm
    1.24
    xtap
    1.10
     guess
    1.04
     suppose
    1.03
    sth
    0.97
     presume
    0.96
    UC
    0.95
    've
    0.95
    rene
    0.95
    nex
    0.92
    Activations Density 0.208%

    No Known Activations