© 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. 0-RES-JB
    11. 6343
    Prev
    Next
    INDEX
    Explanations

    explicit statements of caution or warning

    oai_token-act-pair · gpt-3.5-turbo

    terms that indicate warnings or limitations, particularly those related to caveats and disclaimers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vict
    -0.74
     senseless
    -0.74
    acc
    -0.70
    ames
    -0.68
    agram
    -0.66
    vict
    -0.64
    nan
    -0.64
     instantly
    -0.64
    elect
    -0.63
     litter
    -0.62
    POSITIVE LOGITS
     caveat
    3.49
     caveats
    3.22
     disclaimer
    2.28
     downside
    2.13
     drawback
    1.83
     disclaim
    1.68
     aster
    1.42
     drawbacks
    1.39
     nuance
    1.24
     qualifier
    1.12
    Activations Density 0.047%

    No Known Activations