© 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. 8-RES-JB
    11. 22406
    Prev
    Next
    INDEX
    Explanations

    numbers and special characters in sequences

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or scores in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icter
    -0.71
     Mub
    -0.69
     Nay
    -0.69
     plagiar
    -0.66
     ANC
    -0.60
     Sina
    -0.60
     Sidd
    -0.59
     Abd
    -0.59
     Ae
    -0.58
     Editors
    -0.58
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.68
    Page
    0.67
    riger
    0.65
    Buyable
    0.65
    姫
    0.63
    natureconservancy
    0.60
    gam
    0.59
    asured
    0.59
    keye
    0.57
    aylor
    0.57
    Activations Density 0.107%

    No Known Activations