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. 10552
    Prev
    Next
    INDEX
    Explanations

    numeric data related to statistics in sports

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics related to sports performance

    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
    orah
    -0.68
    bara
    -0.66
    bek
    -0.64
    layer
    -0.61
    grave
    -0.60
    nah
    -0.60
    marks
    -0.60
    actionDate
    -0.59
    eyes
    -0.59
    ibrarian
    -0.59
    POSITIVE LOGITS
     appearances
    1.25
     outings
    1.20
     games
    1.16
     contests
    1.06
     innings
    1.02
     starts
    0.96
     career
    0.95
     matches
    0.93
     attempts
    0.90
     trips
    0.82
    Activations Density 0.066%

    No Known Activations