© 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. 12562
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports leagues, specifically the Premier League

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Prem" or "premature," indicating a focus on premature topics or items

    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
    glers
    -0.94
     MacArthur
    -0.78
    gers
    -0.71
    books
    -0.70
     Hedge
    -0.69
    ger
    -0.68
    finder
    -0.64
     juggling
    -0.63
     ãĤµ
    -0.62
     paths
    -0.60
    POSITIVE LOGITS
    iership
    1.20
    ises
    1.15
    ature
    1.11
    ortal
    1.10
    otor
    1.05
    inent
    1.05
    arks
    1.03
    iere
    1.01
    inence
    1.01
    iers
    0.98
    Activations Density 0.033%

    No Known Activations