© 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. 10-RES-JB
    11. 5820
    Prev
    Next
    INDEX
    Explanations

    Latin characters that are not typically found in English texts

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols in non-standard text formats

    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
    humans
    -0.68
     mileage
    -0.60
     nonpartisan
    -0.60
    ters
    -0.60
     stag
    -0.60
     tabletop
    -0.59
     flo
    -0.58
     bidder
    -0.57
     damned
    -0.57
     RTX
    -0.57
    POSITIVE LOGITS
    е
    1.27
    и
    1.19
    ÑĮ
    1.15
    ãģĨ
    1.11
    ÑĤ
    1.06
    а
    1.03
    н
    1.00
    Ñĥ
    1.00
    ا
    0.99
    alid
    0.99
    Activations Density 0.026%

    No Known Activations