© 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 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. 19762
    Prev
    Next
    INDEX
    Explanations

    contractions and negative words

    oai_token-act-pair · gpt-3.5-turbo

    negative statements or sentiments, particularly using contractions of "would 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
     Compass
    -0.68
    API
    -0.66
    iaz
    -0.60
    notes
    -0.58
     Thumbnails
    -0.58
    è¦ļéĨĴ
    -0.56
    iddles
    -0.56
     Invisible
    -0.54
    checks
    -0.54
    ¶
    -0.53
    POSITIVE LOGITS
     hesitate
    0.90
     dare
    0.84
     necessarily
    0.83
     tolerate
    0.79
     ordinarily
    0.76
     unheard
    0.74
     bother
    0.74
    enance
    0.74
     normally
    0.73
     surprise
    0.72
    Activations Density 0.091%

    No Known Activations