© 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 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. 3-RES-JB
    11. 20949
    Prev
    Next
    INDEX
    Explanations

    mentions of specific sports events

    oai_token-act-pair · gpt-3.5-turbo

    references to college football bowl games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akin
    -0.75
    abet
    -0.74
    apse
    -0.74
    aft
    -0.68
    utic
    -0.65
    EFF
    -0.64
    ials
    -0.63
    ATHER
    -0.62
    omorphic
    -0.61
     rhet
    -0.61
    POSITIVE LOGITS
     Bowl
    1.11
    aneers
    0.84
    bowl
    0.84
    bler
    0.81
    ilet
    0.81
    Coach
    0.77
     Tours
    0.75
     bowls
    0.73
     Players
    0.70
     halftime
    0.69
    Activations Density 0.011%

    No Known Activations