© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12528
    Prev
    Next
    INDEX
    Explanations

    contractions, specifically identifying the word "isn't"

    oai_token-act-pair · gpt-3.5-turbo

    contractions and phrases that express doubt or questioning

    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
    cedes
    -0.65
    lly
    -0.59
    laun
    -0.59
    leaders
    -0.59
     embroiled
    -0.58
    collect
    -0.58
    perty
    -0.58
     indebted
    -0.57
     filib
    -0.57
     facult
    -0.56
    POSITIVE LOGITS
    ometimes
    0.73
    hee
    0.67
    ?),
    0.66
    ttp
    0.65
     Thou
    0.63
    )),
    0.62
    )?
    0.61
    ?).
    0.60
    uits
    0.60
    9999
    0.60
    Activations Density 0.094%

    No Known Activations