© 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. 9-RES-JB
    11. 18443
    Prev
    Next
    INDEX
    Explanations

    whether a statement is negated or not

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating negation or the concept of 'not'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riad
    -0.65
     Quarterly
    -0.61
    æ©Ł
    -0.61
     Kazakh
    -0.60
     Yuan
    -0.59
     Armory
    -0.58
    omics
    -0.58
    antha
    -0.58
    eteenth
    -0.58
    edience
    -0.58
    POSITIVE LOGITS
    epad
    1.19
    hin
    1.14
    ched
    0.92
     depending
    0.92
     necessarily
    0.89
     anymore
    0.83
    eworthy
    0.83
    ches
    0.82
    ifies
    0.80
     versa
    0.75
    Activations Density 0.059%

    No Known Activations