Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 20470
    Prev
    Next
    INDEX
    Explanations

    names and terms related to specific individuals, particularly with the prefix "Kh" and containing a mix of letters and numbers

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to specific geographic locations and associated individuals

    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
    ãĤ¢ãĥ«
    -0.62
    ãĥĩãĤ£
    -0.59
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.58
    ãĥł
    -0.58
    ãĤ½
    -0.58
    yip
    -0.56
    SOURCE
    -0.55
    BILITIES
    -0.55
     Finch
    -0.55
    ãĥĩ
    -0.55
    POSITIVE LOGITS
    obin
    0.93
    chev
    0.90
    enei
    0.77
    schild
    0.73
    src
    0.71
    omer
    0.70
    Ń
    0.69
    ¦
    0.69
    bang
    0.69
    nir
    0.68
    Activations Density 0.082%

    No Known Activations