© 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 12288
    9. 8-RES_FS12288-JB
    11. 9509
    Prev
    Next
    INDEX
    Explanations

    references to time or temporal relationships

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    113
    +0.10
    0.4%
    301
    +0.09
    0.4%
    380
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.10
    0.03
    380
    +0.09
    0.03
    253
    +0.09
    0.03
    Negative Logits
    odor
    -0.70
    haar
    -0.68
    ocracy
    -0.65
    DNA
    -0.62
    Bal
    -0.60
    lde
    -0.60
     Mecca
    -0.59
    REL
    -0.57
     Camel
    -0.57
    crow
    -0.57
    POSITIVE LOGITS
    etheless
    1.05
    noon
    0.95
     versions
    0.90
     installments
    0.85
    than
    0.83
     editions
    0.83
    iations
    0.82
     iterations
    0.82
    iated
    0.81
     stages
    0.81
    Activations Density 0.051%

    No Known Activations