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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 23798
    Prev
    Next
    INDEX
    Explanations

    any occurrence of the phrase 'may not' or 'might not'

    oai_token-act-pair · gpt-3.5-turbo

    negations and expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rebellion
    -0.73
     Painting
    -0.71
     Fuji
    -0.70
     Strategy
    -0.66
     è
    -0.65
    Trivia
    -0.61
     Tactical
    -0.61
     Novel
    -0.60
     Pure
    -0.58
    å¥
    -0.57
    POSITIVE LOGITS
    hin
    1.06
     necessarily
    1.05
    icably
    0.97
    necess
    0.94
     bother
    0.94
    icable
    0.90
     bothered
    0.85
     underestimate
    0.84
     qualify
    0.83
     even
    0.81
    Activations Density 0.053%

    No Known Activations