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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4559
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams and related terms, particularly the Arizona Coyotes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to locations in Arizona, particularly related to sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     swe
    -0.63
    umber
    -0.62
    fare
    -0.61
    acl
    -0.60
    ulative
    -0.60
    isSpecialOrderable
    -0.58
    ministic
    -0.57
    aware
    -0.57
    hirt
    -0.57
    onut
    -0.56
    POSITIVE LOGITS
     Coyotes
    1.51
     Suns
    1.26
     Cardinals
    1.05
     AZ
    1.03
     Republic
    0.91
    Arizona
    0.89
     Wildcats
    0.89
     Arizona
    0.86
     Wright
    0.82
    Phoenix
    0.81
    Activations Density 0.055%

    No Known Activations