© 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. 7-RES-JB
    11. 13435
    Prev
    Next
    INDEX
    Explanations

    instances where someone is being asked to do something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "asked by" or similar structures indicating someone being requested to do something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     largeDownload
    -0.88
    Runner
    -0.84
    redits
    -0.82
    ational
    -0.73
    prototype
    -0.72
    Reviewed
    -0.71
    heimer
    -0.70
    ines
    -0.70
    ifer
    -0.68
    paces
    -0.67
    POSITIVE LOGITS
     virtue
    0.94
     superiors
    0.76
     parliament
    0.75
     STATS
    0.73
    chance
    0.73
     God
    0.68
     law
    0.67
     Parliament
    0.66
     Wizards
    0.65
     chiefs
    0.65
    Activations Density 0.111%

    No Known Activations