© 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. 1359
    Prev
    Next
    INDEX
    Explanations

    the keyword "sc" at various positions in the text

    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
    659
    +0.13
    0.6%
    167
    +0.12
    0.6%
    251
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.13
    0.02
    588
    +0.12
    0.02
    659
    +0.10
    0.02
    Negative Logits
    elsen
    -0.75
     lapse
    -0.71
     remembrance
    -0.71
    nown
    -0.67
    terday
    -0.64
    emonic
    -0.64
     contender
    -0.63
    heit
    -0.63
    éĹĺ
    -0.62
     acknowledgement
    -0.60
    POSITIVE LOGITS
    rupulous
    1.39
    oops
    1.37
    ammers
    1.27
    ouring
    1.25
    rawling
    1.24
    opes
    1.20
    atters
    1.19
    ribe
    1.18
    rawled
    1.17
    outed
    1.15
    Activations Density 0.009%

    No Known Activations