© 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 24576
    5. 8-RES_FS24576-JB
    6. 22248
    Prev
    Next
    INDEX
    Explanations

    the word "cond" and its variations, indicating its focus on words related to conditions or definitions

    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
    739
    +0.11
    0.5%
    149
    +0.11
    0.5%
    159
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.11
    0.01
    149
    +0.11
    0.01
    352
    +0.10
    0.01
    Negative Logits
    chy
    -0.78
    ngth
    -0.72
    DIR
    -0.70
     Lans
    -0.67
    bang
    -0.66
    sonian
    -0.63
    kaya
    -0.63
    tle
    -0.62
    manship
    -0.62
    ching
    -0.62
    POSITIVE LOGITS
    ominium
    1.31
    ensation
    1.22
    ensed
    1.11
    enser
    1.09
    ensing
    1.07
    itional
    1.04
    uctor
    1.02
    uits
    1.02
    itions
    0.99
    uit
    0.97
    Activations Density 0.023%

    No Known Activations