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. 11742
    Prev
    Next
    INDEX
    Explanations

    links and redirections to external websites

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with links and redirects

    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
    Ĥİ
    -0.69
     autonomy
    -0.69
    vere
    -0.66
    ivities
    -0.62
     Temper
    -0.61
     tumultuous
    -0.59
    chie
    -0.59
     Mechdragon
    -0.57
    terness
    -0.57
     curfew
    -0.56
    POSITIVE LOGITS
    href
    1.58
     URL
    1.46
    links
    1.37
     clicked
    1.31
     url
    1.31
     URLs
    1.30
     link
    1.28
    link
    1.24
     links
    1.23
     bookmark
    1.22
    Activations Density 0.198%

    No Known Activations