© 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. 9338
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives that describe certainty or likelihood

    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
    551
    +0.14
    0.6%
    139
    +0.12
    0.5%
    679
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.14
    0.07
    139
    +0.12
    0.06
    200
    +0.10
    0.06
    Negative Logits
     adamant
    -0.67
    ASE
    -0.63
     tweeting
    -0.62
    ARCH
    -0.61
     Episode
    -0.60
     careful
    -0.60
     Divinity
    -0.60
     Constant
    -0.59
     Gothic
    -0.59
    omorphic
    -0.59
    POSITIVE LOGITS
     resembles
    1.24
     belongs
    1.21
     reflects
    1.20
     revolves
    1.20
     exists
    1.20
     existed
    1.19
     arose
    1.15
     represents
    1.15
     appears
    1.14
     coincides
    1.14
    Activations Density 0.345%

    No Known Activations