© 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. 6968
    Prev
    Next
    INDEX
    Explanations

    concepts related to personal beliefs and societal norms

    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
    480
    +0.33
    1.6%
    447
    +0.18
    0.9%
    464
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.33
    0.11
    480
    +0.18
    -0.01
    298
    +0.13
    0.06
    Negative Logits
    iple
    -0.68
    xtap
    -0.59
    staking
    -0.56
     explains
    -0.56
     denotes
    -0.56
     refers
    -0.56
     anecd
    -0.55
    Adds
    -0.55
     partName
    -0.54
    ograp
    -0.53
    POSITIVE LOGITS
    )).
    0.80
    ?".
    0.76
    Merit
    0.68
    ".
    0.68
    )))
    0.66
    %.
    0.65
    ))))
    0.64
    !".
    0.63
    Ħ¢
    0.62
    $.
    0.61
    Activations Density 1.846%

    No Known Activations