© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 24176
    Prev
    Next
    INDEX
    Explanations

    words related to thoughts, feelings, and internal experiences

    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
    734
    +0.12
    0.5%
    601
    +0.10
    0.4%
    209
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.01
    232
    +0.10
    0.04
    501
    +0.09
    0.03
    Negative Logits
    steen
    -0.83
    BSD
    -0.68
    liest
    -0.65
    reau
    -0.64
    FUL
    -0.63
    justice
    -0.62
     Pasadena
    -0.62
     Cinderella
    -0.61
    apple
    -0.60
    include
    -0.60
    POSITIVE LOGITS
    xual
    0.82
    osterone
    0.82
    irts
    0.82
    antage
    0.78
    ogl
    0.78
    umatic
    0.76
    andum
    0.75
    Recomm
    0.74
    atable
    0.74
    ronic
    0.73
    Activations Density 0.130%

    No Known Activations