© 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. 10-RES-JB
    11. 21708
    Prev
    Next
    INDEX
    Explanations

    questions with a tone of uncertainty or seeking validation

    oai_token-act-pair · gpt-3.5-turbo

    rhetorical questions and expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    İĭ
    -0.75
    escription
    -0.75
    arde
    -0.68
     satell
    -0.68
    ronics
    -0.67
    luence
    -0.63
    anwhile
    -0.62
     laun
    -0.62
     sket
    -0.62
     describ
    -0.60
    POSITIVE LOGITS
     Nope
    1.88
     YES
    1.86
     Yes
    1.85
     yes
    1.80
    Yes
    1.80
    Absolutely
    1.80
     Absolutely
    1.78
    yes
    1.77
    YES
    1.76
    No
    1.40
    Activations Density 0.237%

    No Known Activations