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. 582
    Prev
    Next
    INDEX
    Explanations

    terms related to technical and professional services across various industries

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to health and medical services

    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
    é¾įå
    -0.72
    ãĤ¨ãĥ«
    -0.66
    é¾įåĸļ士
    -0.58
    ãĤ¢ãĥ«
    -0.58
    called
    -0.57
    Ö¼
    -0.57
    laughs
    -0.57
    unless
    -0.55
    ãĥį
    -0.54
     answ
    -0.53
    POSITIVE LOGITS
     etc
    1.22
     and
    0.84
    ,
    0.84
    ,...
    0.77
     ect
    0.69
     &
    0.68
    ®,
    0.64
    *,
    0.62
    etc
    0.59
     AND
    0.57
    Activations Density 0.315%

    No Known Activations