© 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. 7900
    Prev
    Next
    INDEX
    Explanations

    short phrases or sentences expressing certainty or confidence

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and quotation marks in the text

    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
     intentional
    -0.56
     planned
    -0.55
     automated
    -0.54
     stray
    -0.53
     planning
    -0.53
     advanced
    -0.52
     leve
    -0.51
     formally
    -0.51
     wildlife
    -0.50
     morp
    -0.49
    POSITIVE LOGITS
    ↵Âł
    0.88
    Otherwise
    0.85
    Therefore
    0.85
    Anyway
    0.81
    Thus
    0.79
    <|endoftext|>
    0.79
    Similarly
    0.79
    Likewise
    0.79
    Nevertheless
    0.78
    Moreover
    0.76
    Activations Density 0.688%

    No Known Activations