© 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
    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. 6782
    Prev
    Next
    INDEX
    Explanations

    mentions of specific events or actions happening in sports matches

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" and its context within the text

    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
    hews
    -0.72
    aucus
    -0.70
    Characters
    -0.67
     <+
    -0.66
    trump
    -0.65
    Rock
    -0.64
     Mormons
    -0.64
     Lyft
    -0.63
    ially
    -0.63
    enter
    -0.63
    POSITIVE LOGITS
     Serie
    1.30
     midfield
    1.21
     Portugal
    1.12
     UEFA
    1.03
     Mourinho
    1.02
     Spain
    1.02
     England
    1.02
     Klopp
    1.01
    iesta
    1.01
     Liga
    1.00
    Activations Density 0.098%

    No Known Activations