© 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. 1870
    Prev
    Next
    INDEX
    Explanations

    words related to confidence and certainty

    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
    247
    +0.12
    0.6%
    447
    +0.10
    0.5%
    99
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.12
    0.02
    490
    +0.10
    0.02
    483
    +0.10
    0.02
    Negative Logits
     UCHIJ
    -0.62
    pmwiki
    -0.61
    Pause
    -0.59
    levard
    -0.57
    along
    -0.57
    */(
    -0.56
    sites
    -0.56
    kay
    -0.56
    ravings
    -0.55
    theme
    -0.55
    POSITIVE LOGITS
    ially
    1.22
     enough
    1.09
    iated
    1.01
    ius
    0.77
    ively
    0.77
    enough
    0.76
    iably
    0.76
    uine
    0.72
    rons
    0.70
    ial
    0.68
    Activations Density 0.044%

    No Known Activations