© 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 12288
    5. 8-RES_FS12288-JB
    6. 617
    Prev
    Next
    INDEX
    Explanations

    references to looking closely at or examining something in a specific context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    373
    +0.19
    0.9%
    715
    +0.13
    0.6%
    671
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    715
    +0.19
    0.05
    750
    +0.13
    0.04
    429
    +0.11
    0.04
    Negative Logits
    Els
    -0.74
    burgh
    -0.72
    Es
    -0.69
    atile
    -0.67
    Guest
    -0.63
    Bs
    -0.63
    phrine
    -0.63
    Adds
    -0.63
    olicited
    -0.62
    WC
    -0.61
    POSITIVE LOGITS
     hindsight
    0.77
    »Ĵ
    0.75
     carefully
    0.75
     google
    0.74
     maths
    0.69
    ¿½
    0.68
     retrospect
    0.67
     arithmetic
    0.66
     analyse
    0.65
    Econom
    0.64
    Activations Density 0.286%

    No Known Activations