© 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. 0-RES-JB
    11. 2640
    Prev
    Next
    INDEX
    Explanations

    obviously mentioned elements or situations

    oai_token-act-pair · gpt-3.5-turbo

    the word "obviously" and its variations, indicating a focus on statements that assert some degree of certainty or clarity

    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
    ury
    -0.64
    zen
    -0.63
     refuge
    -0.60
    heny
    -0.60
    held
    -0.59
    aud
    -0.57
    est
    -0.57
    lee
    -0.54
     County
    -0.53
     monthly
    -0.53
    POSITIVE LOGITS
     obviously
    3.13
     evidently
    2.06
     clearly
    1.83
     certainly
    1.83
     undoubtedly
    1.79
     definitely
    1.78
     presumably
    1.76
     understandably
    1.71
     admittedly
    1.68
     Obviously
    1.67
    Activations Density 0.016%

    No Known Activations