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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 3259
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports news or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Sports."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ean
    -0.71
    vironment
    -0.71
    semb
    -0.70
    iflower
    -0.69
    nces
    -0.69
    onyms
    -0.64
     miscar
    -0.64
    ocument
    -0.63
    ipop
    -0.63
    arine
    -0.63
    POSITIVE LOGITS
    Sport
    1.18
     Sports
    1.11
    Sports
    1.11
    sports
    1.03
     Illustrated
    0.94
    Club
    0.91
     Club
    0.90
    fan
    0.89
     Clubs
    0.86
    club
    0.84
    Activations Density 0.007%

    No Known Activations