© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RES-JB
    11. 19053
    Prev
    Next
    INDEX
    Explanations

    instances where the text includes the phrase "may not"

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rebellion
    -0.68
     Painting
    -0.67
     Fuji
    -0.64
     Strategy
    -0.64
    å¥
    -0.63
     Pist
    -0.60
     Strategic
    -0.60
    plates
    -0.59
    ãĤ¸
    -0.58
     Incredible
    -0.58
    POSITIVE LOGITS
     necessarily
    1.14
    hin
    1.04
    necess
    1.02
    icably
    0.90
     underestimate
    0.88
     qualify
    0.84
     even
    0.84
    icable
    0.84
     bother
    0.82
     swayed
    0.82
    Activations Density 0.041%

    No Known Activations