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. 11-RES-JB
    6. 19578
    Prev
    Next
    INDEX
    Explanations

    phrases related to time frames

    oai_token-act-pair · gpt-3.5-turbo

    patterns related to sports performance and statistics over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    mart
    -0.78
    qs
    -0.61
     urgent
    -0.61
     Cosponsors
    -0.61
    chin
    -0.59
    "},{"
    -0.58
     âĺ
    -0.57
     GMT
    -0.57
     extrad
    -0.56
     Ibid
    -0.56
    POSITIVE LOGITS
     offseason
    1.27
     preseason
    1.25
     postseason
    1.19
     seasons
    1.15
     playoffs
    1.08
    season
    1.07
     season
    1.04
    Season
    1.02
     rookies
    1.00
     rookie
    0.98
    Activations Density 0.145%

    No Known Activations