© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 2693
    Prev
    Next
    INDEX
    Explanations

    references to a particular sports team, the "Colts."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Indianapolis Colts football team

    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
    lly
    -0.78
    nces
    -0.76
    akespe
    -0.73
    stage
    -0.73
    selection
    -0.71
    gettable
    -0.70
    ovych
    -0.65
    trigger
    -0.64
    lling
    -0.63
    vae
    -0.62
    POSITIVE LOGITS
     Colts
    1.26
    ilage
    0.91
    sburg
    0.83
    apolis
    0.78
     Broncos
    0.78
    orius
    0.77
     Jaguars
    0.77
     Iro
    0.75
     Pacers
    0.75
     Titans
    0.74
    Activations Density 0.006%

    No Known Activations