© 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. 24240
    Prev
    Next
    INDEX
    Explanations

    references to various states of being and actions involving uncertainty or inadequacy

    oai_token-act-pair · gpt-4o-miniTriggered 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
    315
    +0.12
    0.5%
    378
    +0.11
    0.5%
    233
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    698
    +0.12
    0.02
    767
    +0.11
    0.02
    233
    +0.10
    0.02
    Negative Logits
    JA
    -0.68
     Axe
    -0.68
    axis
    -0.66
     Cologne
    -0.66
    CS
    -0.63
     Seahawks
    -0.62
     ABE
    -0.62
     Kath
    -0.62
     marches
    -0.62
     goose
    -0.61
    POSITIVE LOGITS
    not
    1.20
     not
    1.10
    nt
    0.98
    NOT
    0.98
     NOT
    0.96
    Not
    0.93
    lessness
    0.91
     Not
    0.91
     unob
    0.89
     didnt
    0.87
    Activations Density 0.104%

    No Known Activations