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. 12-RES-JB
    6. 15179
    Prev
    Next
    INDEX
    Explanations

    dates or years written in four digits

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    significant events and milestones in sports and entertainment contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nown
    -0.95
    utterstock
    -0.77
    sic
    -0.74
    warn
    -0.71
    obia
    -0.71
    uphem
    -0.70
    ickr
    -0.69
    olen
    -0.69
    afety
    -0.69
    heit
    -0.66
    POSITIVE LOGITS
     WWE
    1.46
     Wrestle
    1.41
     UFC
    1.40
     NASL
    1.40
     NHL
    1.33
     MLB
    1.32
     NBA
    1.31
     NRL
    1.30
     Knicks
    1.29
     Sounders
    1.28
    Activations Density 1.312%

    No Known Activations