© 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. 6888
    Prev
    Next
    INDEX
    Explanations

    contractions with the word "don't" in them

    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
    373
    +0.12
    0.5%
    603
    +0.10
    0.5%
    428
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    603
    +0.12
    0.05
    696
    +0.10
    0.05
    431
    +0.09
    0.04
    Negative Logits
     newcom
    -0.66
     mir
    -0.62
     Published
    -0.60
     Hum
    -0.60
     Unc
    -0.59
     Beaut
    -0.58
     Adv
    -0.57
     caster
    -0.57
     Proposition
    -0.57
     Authors
    -0.57
    POSITIVE LOGITS
    't
    1.29
    ned
    1.01
    its
    0.92
    ÃŃ
    0.87
    NT
    0.85
    iencies
    0.85
    itely
    0.85
    uts
    0.83
    n
    0.83
    acent
    0.82
    Activations Density 0.082%

    No Known Activations