© 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. 8011
    Prev
    Next
    INDEX
    Explanations

    town or city names

    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
    0.6%
    746
    +0.12
    0.6%
    332
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    515
    +0.12
    0.01
    232
    +0.12
    0.01
    373
    +0.12
    -0.00
    Negative Logits
    NRS
    -0.75
     horm
    -0.67
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.63
     MPG
    -0.63
     mitigating
    -0.62
     cuff
    -0.60
    Article
    -0.59
    IDA
    -0.59
     hump
    -0.59
     Quantum
    -0.59
    POSITIVE LOGITS
    cheon
    1.01
    eer
    1.00
    gha
    0.98
    emouth
    0.97
    eers
    0.97
    thood
    0.97
    gement
    0.97
    gements
    0.93
    tesy
    0.91
    cy
    0.91
    Activations Density 0.025%

    No Known Activations