© 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. 9597
    Prev
    Next
    INDEX
    Explanations

    the word "So" with a high activation value

    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
    314
    +0.11
    0.5%
    55
    +0.10
    0.5%
    320
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.11
    0.03
    589
    +0.10
    0.02
    559
    +0.10
    0.02
    Negative Logits
    theless
    -0.69
    DERR
    -0.68
     omission
    -0.64
     knots
    -0.63
     contradiction
    -0.62
     equity
    -0.62
     resemblance
    -0.61
     aristocracy
    -0.59
     apprehension
    -0.59
     anticipation
    -0.58
    POSITIVE LOGITS
    ppy
    1.10
    oths
    1.09
    fter
    1.08
    aring
    1.07
    arin
    1.07
    FTWARE
    1.06
    aked
    1.05
    bered
    1.05
    oner
    1.04
    vere
    1.03
    Activations Density 0.046%

    No Known Activations