© 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. 8060
    Prev
    Next
    INDEX
    Explanations

    proper nouns and named entities

    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
    +0.14
    0.6%
    447
    +0.13
    0.6%
    98
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.14
    -0.00
    167
    +0.13
    0.01
    727
    +0.10
    0.03
    Negative Logits
    ––
    -0.66
    -"
    -0.63
    etsy
    -0.61
     Buckley
    -0.61
     CPC
    -0.60
    )"
    -0.59
     NEO
    -0.59
    ×ķ
    -0.59
     Dire
    -0.59
     Nept
    -0.58
    POSITIVE LOGITS
    ategory
    0.78
    htaking
    0.70
    itionally
    0.69
     <-
    0.66
    oreAnd
    0.66
    ruciating
    0.65
    reetings
    0.65
    vernight
    0.64
    eatures
    0.64
    ometime
    0.63
    Activations Density 0.266%

    No Known Activations