© 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 49152
    9. 8-RES_FS49152-JB
    11. 45678
    Prev
    Next
    INDEX
    Explanations

    the word "honestly" used in various contexts, indicating a focus on genuine or sincere expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    200
    +0.12
    0.5%
    246
    +0.10
    0.5%
    421
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    246
    +0.12
    0.01
    307
    +0.10
    0.01
    200
    +0.10
    0.01
    Negative Logits
     Klu
    -0.72
     Blades
    -0.68
    tein
    -0.67
     foes
    -0.66
    aeus
    -0.64
     Landing
    -0.64
     Sale
    -0.62
     Sparkle
    -0.62
    VK
    -0.61
     GOODMAN
    -0.61
    POSITIVE LOGITS
     doubted
    0.77
     believe
    0.74
     speaking
    0.73
    imated
    0.73
    zers
    0.71
    ãĥĩãĤ£
    0.70
     believed
    0.69
    ardless
    0.69
    ounded
    0.69
     amazed
    0.68
    Activations Density 0.006%

    No Known Activations