© 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. 7333
    Prev
    Next
    INDEX
    Explanations

    phrases used for emphasizing or transitioning in writing

    oai_token-act-pair · gpt-3.5-turbo

    the presence of commas, indicating a list or a pause in thought

    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
    ords
    -0.63
    irc
    -0.59
    ipel
    -0.56
    hell
    -0.55
    ield
    -0.55
    cott
    -0.55
    BuyableInstoreAndOnline
    -0.55
     shell
    -0.54
     REPL
    -0.54
    eta
    -0.54
    POSITIVE LOGITS
     albeit
    0.85
     however
    0.82
     moreover
    0.74
     although
    0.73
    Dri
    0.72
     somew
    0.71
     though
    0.70
     namely
    0.67
     lest
    0.67
     anecd
    0.67
    Activations Density 0.194%

    No Known Activations