© 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 EvalsExportsinterp-engineNEWAPI 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. 9290
    Prev
    Next
    INDEX
    Explanations

    words related to negation

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases punctuated with commas or specific qualifiers

    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
    ounded
    -0.67
    gypt
    -0.64
    ende
    -0.62
    alone
    -0.60
     Equip
    -0.59
    oufl
    -0.58
    mud
    -0.57
     feasibility
    -0.56
     chains
    -0.56
     Klux
    -0.56
    POSITIVE LOGITS
     sir
    0.84
     whatsoever
    0.80
    onsense
    0.79
     nor
    0.73
     thank
    0.68
     except
    0.65
    æĪ
    0.61
     Answer
    0.61
    Shift
    0.60
     exaggeration
    0.60
    Activations Density 0.053%

    No Known Activations