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. 7-RES-JB
    6. 17049
    Prev
    Next
    INDEX
    Explanations

    information structured in a news article format

    oai_token-act-pair · gpt-3.5-turbo

    announcements or reports regarding significant events or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    username
    -0.55
    mg
    -0.54
     Loki
    -0.54
     Auction
    -0.54
     beetles
    -0.53
     Draco
    -0.51
     Ultron
    -0.51
     Daredevil
    -0.51
     Zombies
    -0.51
     Squadron
    -0.51
    POSITIVE LOGITS
    WASHINGTON
    0.85
    eport
    0.70
    SHARE
    0.69
     VIDE
    0.67
    SAN
    0.66
     SAN
    0.64
    GREEN
    0.64
    ccording
    0.64
    ASHINGTON
    0.64
     Ago
    0.64
    Activations Density 0.349%

    No Known Activations