© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 5696
    Prev
    Next
    INDEX
    Explanations

    adverbs that express certainty or correctness

    oai_token-act-pair · gpt-3.5-turbo

    assertive and qualifying adverbs that emphasize reality or technicality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    regate
    -0.86
    enaries
    -0.79
    Tex
    -0.72
    icip
    -0.71
    atern
    -0.71
    atem
    -0.69
    ults
    -0.68
    eral
    -0.68
    ilst
    -0.68
    osion
    -0.67
    POSITIVE LOGITS
     irrelevant
    1.07
     indicative
    1.00
     synonymous
    0.99
     preferable
    0.96
     incompatible
    0.96
     meaningless
    0.94
     worth
    0.93
     easier
    0.91
     impossible
    0.87
     outdated
    0.85
    Activations Density 0.225%

    No Known Activations