© 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. 9-RES-JB
    11. 11415
    Prev
    Next
    INDEX
    Explanations

    contractions with "n't" indicating negation

    oai_token-act-pair · gpt-3.5-turbo

    negations, particularly the phrase "didn't" and its variations

    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
    ¿½
    -0.70
    interstitial
    -0.66
    itiz
    -0.66
     arsen
    -0.64
     Continued
    -0.62
     antioxid
    -0.62
    accompan
    -0.61
     Mania
    -0.61
    edIn
    -0.60
    Ĭ±
    -0.59
    POSITIVE LOGITS
     hesitate
    1.21
     realize
    1.15
     realise
    1.14
     bother
    1.13
     specify
    1.09
     necessarily
    1.08
     anticipate
    1.00
     originate
    0.98
     succeed
    0.98
     mention
    0.98
    Activations Density 0.125%

    No Known Activations