© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10721
    Prev
    Next
    INDEX
    Explanations

    sports-related phrases involving field position or performance

    oai_token-act-pair · gpt-3.5-turbo

    references to sports fields or playing areas

    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
    ilyn
    -0.76
     Seas
    -0.75
    itarian
    -0.71
    éĹĺ
    -0.71
    uble
    -0.69
     Sisters
    -0.65
    bian
    -0.63
     Reich
    -0.63
     BaseType
    -0.63
     Bolt
    -0.63
    POSITIVE LOGITS
    ers
    0.89
    keepers
    0.84
    keeper
    0.84
    field
    0.81
    er
    0.80
    backer
    0.78
    Tur
    0.77
     scoreboard
    0.77
    fields
    0.76
    runners
    0.76
    Activations Density 0.022%

    No Known Activations