© 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. 6232
    Prev
    Next
    INDEX
    Explanations

    numeric values in a particular range related to quantities, prices, and statistics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to voting, political decisions, and socioeconomic issues

    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
    onis
    -0.56
    ãĤ¢ãĥ«
    -0.53
     ACTIONS
    -0.52
    ":"/
    -0.51
    lez
    -0.50
    nown
    -0.50
     depress
    -0.49
     toget
    -0.49
     alot
    -0.49
     somew
    -0.47
    POSITIVE LOGITS
     versus
    1.00
     and
    0.95
     plus
    0.78
     };
    0.78
     or
    0.74
    -,
    0.73
     respectively
    0.73
     followed
    0.72
    .;
    0.72
     vs
    0.72
    Activations Density 1.107%

    No Known Activations