© 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. 19401
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating distance or direction

    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
    608
    +0.13
    0.6%
    669
    +0.12
    0.6%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.13
    0.03
    608
    +0.12
    0.03
    533
    +0.11
    0.03
    Negative Logits
    ©¶æ¥µ
    -0.88
    Lic
    -0.72
    laughter
    -0.71
    few
    -0.71
    wang
    -0.69
    IER
    -0.67
    vic
    -0.67
    fif
    -0.67
    had
    -0.66
    soon
    -0.66
    POSITIVE LOGITS
     afar
    0.79
     home
    0.77
     civilisation
    0.74
     shore
    0.73
     whence
    0.72
    ables
    0.70
     civilization
    0.70
     them
    0.70
     caring
    0.69
     anything
    0.69
    Activations Density 0.068%

    No Known Activations