© 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. 6884
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the raising or questioning of issues, concerns, or doubts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the act of raising questions or issues

    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
    acs
    -0.66
    Cass
    -0.66
    é¾įåĸļ士
    -0.63
    duration
    -0.62
    mates
    -0.62
    ungle
    -0.61
    location
    -0.61
    webkit
    -0.60
    xs
    -0.59
     Mamm
    -0.59
    POSITIVE LOGITS
     questions
    1.62
     eyebrows
    1.49
     concerns
    1.39
     doubts
    1.38
     suspicions
    1.31
     question
    1.22
     Questions
    1.19
     fears
    1.14
     issues
    1.12
     alarms
    1.12
    Activations Density 0.087%

    No Known Activations