© 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. 6-RES-JB
    11. 7863
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases indicating certainty or emphasis, often with the phrase "in fact"

    oai_token-act-pair · gpt-3.5-turbo

    statements asserting the truth of claims or facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.79
    bye
    -0.69
     Crown
    -0.64
     Greenwood
    -0.63
     Citiz
    -0.62
     eyebrows
    -0.61
     hairs
    -0.60
     banana
    -0.60
     lungs
    -0.59
    South
    -0.58
    POSITIVE LOGITS
    ional
    1.12
    netflix
    0.82
    REP
    0.79
    çī
    0.74
    olkien
    0.73
    uality
    0.71
    opus
    0.70
     Obj
    0.69
    akes
    0.69
    abetic
    0.68
    Activations Density 0.017%

    No Known Activations