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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14054
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negation or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    phrases that negate or dismiss certain ideas or concepts

    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
    Reviewed
    -0.71
     Metatron
    -0.67
     whichever
    -0.57
     Polk
    -0.57
    GBT
    -0.56
     Orth
    -0.55
     Stew
    -0.54
    perse
    -0.54
    kefeller
    -0.53
    phrine
    -0.53
    POSITIVE LOGITS
    xious
    0.90
     uncertain
    0.90
    onday
    0.89
    xus
    0.87
    ct
    0.78
     conceivable
    0.78
     avail
    0.74
     particular
    0.73
    osphere
    0.72
    otrop
    0.70
    Activations Density 0.028%

    No Known Activations