© 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. 12-RES-JB
    11. 2658
    Prev
    Next
    INDEX
    Explanations

    contractions that indicate negation or uncertainty

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    negations, specifically phrases that denote a lack or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ò
    -1.50
    ñ
    -1.45
    Đ
    -1.40
    Č
    -1.40
    ø
    -1.39
    Ą
    -1.39
    ý
    -1.39
    õ
    -1.39
    Ā
    -1.39
    ù
    -1.39
    POSITIVE LOGITS
     necessarily
    1.10
     mind
    1.03
     bother
    1.03
     really
    1.02
     even
    1.01
     exactly
    1.01
     wanna
    0.97
     care
    0.97
     need
    0.97
     know
    0.95
    Activations Density 0.179%

    No Known Activations