© 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. 18656
    Prev
    Next
    INDEX
    Explanations

    the word "then" at the beginning of a sentence

    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
    204
    +0.12
    0.5%
    372
    +0.10
    0.4%
    273
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    761
    +0.12
    0.03
    204
    +0.10
    0.03
    301
    +0.10
    0.03
    Negative Logits
    tumblr
    -0.69
    çīĪ
    -0.68
    dinand
    -0.66
     Cantor
    -0.66
    utan
    -0.65
    è¦ļéĨĴ
    -0.64
    vernment
    -0.64
     è£ıç
    -0.64
    #$#$
    -0.63
    rera
    -0.62
    POSITIVE LOGITS
     considerably
    0.89
    ened
    0.78
     feelings
    0.74
     tone
    0.74
     somewhat
    0.73
     nerv
    0.72
    heartedly
    0.71
     throttle
    0.71
    hearted
    0.71
     condensed
    0.70
    Activations Density 0.155%

    No Known Activations