© 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. 10980
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences containing the word "interesting," "remarkable," "strange," or "astonishing."

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing interest or notable observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "is" preceded by a synonym of "remarkable" or "strange" and followed by "that," "how" or "the"

    Explanation Uploaded by User
    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
     throats
    -0.83
     throat
    -0.76
     spons
    -0.68
    idation
    -0.66
    ona
    -0.64
    assad
    -0.63
     fitt
    -0.63
    ente
    -0.63
     slump
    -0.62
    agall
    -0.62
    POSITIVE LOGITS
     parallels
    0.74
    Merit
    0.72
    Appearance
    0.71
     trivia
    0.70
     juxtap
    0.66
    SPONSORED
    0.66
     Exhibit
    0.65
    !--
    0.64
     Solitaire
    0.64
    âĢ¦]
    0.62
    Activations Density 0.266%

    No Known Activations