© 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. 24123
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or structures in text

    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
    507
    +0.11
    0.5%
    720
    +0.09
    0.4%
    222
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.11
    0.04
    73
    +0.09
    0.04
    720
    +0.09
    0.04
    Negative Logits
    asis
    -0.67
    eur
    -0.65
    washer
    -0.65
    ield
    -0.63
    igmatic
    -0.62
    ity
    -0.61
    eus
    -0.61
    PORT
    -0.60
    earable
    -0.60
    =#
    -0.60
    POSITIVE LOGITS
     meanwhile
    1.16
     including
    1.12
     however
    1.02
     rejoice
    1.02
    including
    0.98
     moreover
    0.93
    particularly
    0.91
     alas
    0.88
     especially
    0.88
     beware
    0.87
    Activations Density 0.166%

    No Known Activations