© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 24059
    Prev
    Next
    INDEX
    Explanations

    the word "no" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions indicating the absence of something

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ammad
    -0.78
    leaning
    -0.72
    pak
    -0.67
    ale
    -0.66
    chev
    -0.66
    interstitial
    -0.66
    south
    -0.65
    rex
    -0.65
    SPA
    -0.65
    xtap
    -0.64
    POSITIVE LOGITS
     clue
    1.33
     intention
    1.19
     idea
    1.17
     shortage
    1.12
     qual
    1.11
     illusions
    1.11
     recourse
    1.11
     doubt
    1.08
     obligation
    1.05
     excuse
    1.02
    Activations Density 0.050%

    No Known Activations