© 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. 8-RES-JB
    11. 4156
    Prev
    Next
    INDEX
    Explanations

    mentions of marathons

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to marathons and racing events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olia
    -0.77
    pie
    -0.77
    relation
    -0.72
    vironment
    -0.67
    arial
    -0.66
     warr
    -0.64
    afort
    -0.63
    asley
    -0.61
    Original
    -0.61
    angered
    -0.61
    POSITIVE LOGITS
     runner
    1.14
     runners
    1.06
     endurance
    1.05
     sprint
    0.99
     cycling
    0.95
    bike
    0.91
     cyclist
    0.89
     bike
    0.88
     biking
    0.86
     Cycling
    0.85
    Activations Density 0.147%

    No Known Activations