© 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. 11-RES-JB
    11. 24032
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or possibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or possibility

    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
    SIGN
    -0.70
    advertisement
    -0.68
    enegger
    -0.64
    Reply
    -0.63
    ocker
    -0.62
     Lerner
    -0.62
    OND
    -0.59
     CTR
    -0.59
    kefeller
    -0.58
    oker
    -0.58
    POSITIVE LOGITS
     may
    1.31
    may
    1.06
     MAY
    1.06
     might
    0.85
    might
    0.77
    May
    0.76
     cannot
    0.75
    June
    0.73
     possibly
    0.72
     May
    0.72
    Activations Density 0.066%

    No Known Activations