© 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. 12777
    Prev
    Next
    INDEX
    Explanations

    situations prompting the expectation of a specific outcome or response

    oai_token-act-pair · gpt-3.5-turbo

    expressions of speculation or conjecture

    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
    -0.70
    ictive
    -0.68
     tremend
    -0.67
    ouched
    -0.66
    incible
    -0.63
    elin
    -0.62
    ding
    -0.61
    cember
    -0.60
    alysis
    -0.59
    urable
    -0.59
    POSITIVE LOGITS
     otherwise
    0.78
    enance
    0.70
    DragonMagazine
    0.63
     considering
    0.58
     that
    0.57
     logically
    0.57
    rett
    0.56
     forgiven
    0.56
    oppers
    0.56
     oneself
    0.55
    Activations Density 0.118%

    No Known Activations