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. 10-RES-JB
    6. 1635
    Prev
    Next
    INDEX
    Explanations

    websites and social media handles

    oai_token-act-pair · gpt-3.5-turbo

    URL patterns and web addresses

    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
     jaw
    -0.59
     culinary
    -0.58
     Charl
    -0.58
     demolition
    -0.58
     Mara
    -0.57
    ATIVE
    -0.57
     ageing
    -0.57
    ãĤ¨ãĥ«
    -0.56
     situational
    -0.56
     audits
    -0.55
    POSITIVE LOGITS
    com
    1.60
    icio
    1.04
    co
    1.00
    tv
    1.00
    org
    0.97
    tumblr
    0.95
    edu
    0.95
    ca
    0.92
    net
    0.91
    biz
    0.90
    Activations Density 0.037%

    No Known Activations