© 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. 23349
    Prev
    Next
    INDEX
    Explanations

    terms related to questions and actions in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    phrases and questions that involve actions or inquiries about doing something

    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
    catentry
    -0.69
    mast
    -0.66
    ahime
    -0.63
    irms
    -0.62
    aples
    -0.60
    bis
    -0.57
     succumbed
    -0.56
    akable
    -0.56
    ullivan
    -0.56
     fundament
    -0.54
    POSITIVE LOGITS
    ?
    1.82
    ?:
    1.70
    !?
    1.65
    ?!
    1.64
    ?"
    1.55
    ?,
    1.53
    ??
    1.52
    ???
    1.49
    ?'
    1.44
    ?",
    1.42
    Activations Density 0.200%

    No Known Activations