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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 15927
    Prev
    Next
    INDEX
    Explanations

    words or phrases containing non-English characters

    oai_token-act-pair · gpt-3.5-turbo

    specific symbols and characters, possibly indicating non-standard text or formatting issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ters
    -0.65
    lisher
    -0.64
    teen
    -0.64
     mileage
    -0.61
    humans
    -0.60
    rette
    -0.60
     stag
    -0.59
     bidder
    -0.59
     flo
    -0.59
     streak
    -0.59
    POSITIVE LOGITS
    е
    1.03
    ÑĮ
    0.99
    ãģĨ
    0.96
    ãĤ£
    0.91
    ا
    0.90
    alid
    0.90
    и
    0.90
    女
    0.90
    Ãł
    0.89
    å®
    0.89
    Activations Density 0.043%

    No Known Activations