© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 8568
    Prev
    Next
    INDEX
    Explanations

    instances of phrases or clauses expressing criticism or disagreement

    oai_token-act-pair · gpt-3.5-turbo

    the adverb "just" in various contexts

    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
    lore
    -0.72
    eers
    -0.63
    ahime
    -0.59
     Nurs
    -0.58
     Archdemon
    -0.57
    apolis
    -0.57
     appell
    -0.56
    pora
    -0.56
    nation
    -0.55
    ught
    -0.54
    POSITIVE LOGITS
    ifications
    1.16
    ifiable
    1.11
    cause
    0.88
    itia
    0.88
     because
    0.87
    because
    0.86
    if
    0.84
    ifying
    0.81
    inian
    0.78
     desserts
    0.78
    Activations Density 0.067%

    No Known Activations