© 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. 12755
    Prev
    Next
    INDEX
    Explanations

    questions uttered by different individuals

    oai_token-act-pair · gpt-3.5-turbo

    questions that prompt inquiry or clarification

    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
     endorsements
    -0.71
     shortcuts
    -0.66
     affili
    -0.66
     limb
    -0.62
     surviving
    -0.60
    phas
    -0.60
     spo
    -0.60
    estyle
    -0.59
     bunk
    -0.58
     synchronized
    -0.57
    POSITIVE LOGITS
     asked
    1.74
     asks
    1.71
     inquired
    1.63
     wondered
    1.35
     Asked
    1.35
     quer
    1.34
     Questions
    1.29
     questions
    1.28
     enqu
    1.27
     ask
    1.25
    Activations Density 0.091%

    No Known Activations