© 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. 11836
    Prev
    Next
    INDEX
    Explanations

    differences in names and aliases for individuals

    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
    480
    +0.46
    2.4%
    266
    +0.12
    0.6%
    420
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.46
    0.01
    266
    +0.12
    0.09
    393
    +0.10
    0.10
    Negative Logits
    ateurs
    -0.74
    ariat
    -0.71
     tackling
    -0.67
    rive
    -0.65
    ouble
    -0.65
    porate
    -0.65
     backlog
    -0.64
     incremental
    -0.63
    seless
    -0.62
     workforce
    -0.61
    POSITIVE LOGITS
     resemblance
    1.01
     resemb
    0.95
     similarities
    0.91
     similarity
    0.89
     canon
    0.86
    canon
    0.83
     presumably
    0.82
     mentions
    0.82
    tymology
    0.81
     references
    0.81
    Activations Density 1.105%

    No Known Activations