© 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. 11-RES-JB
    11. 21091
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative consequences or issues

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or formatting that seems to represent special symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    enegger
    -0.87
    ãģ®éŃĶ
    -0.85
    gow
    -0.76
    enburg
    -0.74
    ements
    -0.70
     compuls
    -0.68
    worthiness
    -0.66
     whichever
    -0.63
     PTS
    -0.63
    iator
    -0.62
    POSITIVE LOGITS
    ¹
    1.77
    ³
    1.71
    ¿
    1.69
    ¦
    1.64
    ¬
    1.64
    µ
    1.54
    ¾
    1.54
    ¥
    1.54
    ¸
    1.50
    ¡
    1.46
    Activations Density 0.015%

    No Known Activations