© 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 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. 10742
    Prev
    Next
    INDEX
    Explanations

    words related to freedom, censorship, and political commentary

    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
    593
    +0.13
    0.6%
    503
    +0.12
    0.5%
    102
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.13
    0.02
    331
    +0.12
    0.02
    251
    +0.10
    0.02
    Negative Logits
    anwhile
    -0.75
    pheus
    -0.70
     Nanto
    -0.68
    tery
    -0.66
     Origins
    -0.64
    SHIP
    -0.64
     Doctors
    -0.63
    _>
    -0.63
     Christy
    -0.62
     Dynamics
    -0.61
    POSITIVE LOGITS
    ashed
    1.00
    ishable
    0.99
    ported
    0.94
    ipolar
    0.92
    inding
    0.91
    idden
    0.90
    assuming
    0.89
    athed
    0.89
    isexual
    0.86
    ursed
    0.84
    Activations Density 0.013%

    No Known Activations