© 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. 0-RES-JB
    11. 1539
    Prev
    Next
    INDEX
    Explanations

    words related to negation, specifically the term "Nor."

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "Nor" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERG
    -0.60
    Beast
    -0.59
    aptic
    -0.59
    osis
    -0.56
    éĹ
    -0.56
    IFF
    -0.56
    ell
    -0.55
    EMA
    -0.55
    Finish
    -0.54
    etimes
    -0.53
    POSITIVE LOGITS
     Nor
    3.77
    Nor
    2.54
     nor
    1.77
    nor
    1.65
     NOR
    1.42
     Nay
    1.34
     Rather
    1.21
     Or
    1.14
     Far
    1.10
     Neither
    1.08
    Activations Density 0.008%

    No Known Activations