© 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. 20320
    Prev
    Next
    INDEX
    Explanations

    information related to churches and locations

    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
    640
    +0.31
    1.5%
    700
    +0.09
    0.4%
    469
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.31
    0.07
    469
    +0.09
    0.03
    374
    +0.09
    0.03
    Negative Logits
    xual
    -0.81
    ²¾
    -0.70
    omething
    -0.69
    uly
    -0.68
    ername
    -0.66
    itives
    -0.65
    cius
    -0.64
    ensibly
    -0.63
    nsic
    -0.61
     identity
    -0.61
    POSITIVE LOGITS
    pmwiki
    0.84
    Jere
    0.72
    Tickets
    0.69
    Contribut
    0.68
    CAST
    0.68
    Bonus
    0.68
    ³³³
    0.66
    ↵
    0.66
    Chair
    0.65
    Beta
    0.64
    Activations Density 0.123%

    No Known Activations