© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 18352
    Prev
    Next
    INDEX
    Explanations

    opinions and perspectives expressed by different individuals or groups

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    313
    +0.12
    0.6%
    86
    +0.10
    0.4%
    494
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    313
    +0.12
    0.05
    71
    +0.10
    0.04
    494
    +0.09
    0.05
    Negative Logits
    ocol
    -0.75
    acion
    -0.73
    ibal
    -0.70
    odore
    -0.65
    ories
    -0.65
    fecture
    -0.63
    onduct
    -0.63
    patient
    -0.63
    acus
    -0.63
    ataka
    -0.62
    POSITIVE LOGITS
     observers
    1.15
     commentators
    1.09
     onlook
    1.08
     commenters
    0.98
     pundits
    0.97
     people
    0.94
     economists
    0.92
     critics
    0.92
     attendees
    0.91
     viewers
    0.90
    Activations Density 0.145%

    No Known Activations