© 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 49152
    9. 8-RES_FS49152-JB
    11. 45857
    Prev
    Next
    INDEX
    Explanations

    discussions about government accountability and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    393
    +0.11
    0.5%
    546
    +0.09
    0.4%
    19
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.11
    0.04
    43
    +0.09
    0.03
    517
    +0.09
    0.03
    Negative Logits
    MpServer
    -0.85
    License
    -0.75
    ãĤ´ãĥ³
    -0.70
     redes
    -0.68
    BN
    -0.68
    REDACTED
    -0.65
    ailing
    -0.65
    bishop
    -0.64
    Detailed
    -0.63
    Had
    -0.63
    POSITIVE LOGITS
     invariably
    0.98
     inevitably
    0.93
     usually
    0.90
     chances
    0.81
     typically
    0.78
    usually
    0.74
     they
    0.73
     however
    0.73
     regardless
    0.71
     beware
    0.71
    Activations Density 0.099%

    No Known Activations