© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 7639
    Prev
    Next
    INDEX
    Explanations

    mentions of riders, particularly in the context of sports or events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of riders within the context of events or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aples
    -0.76
    orial
    -0.75
    rontal
    -0.71
     Yale
    -0.68
    ritz
    -0.66
    ihara
    -0.65
     mainland
    -0.65
     pear
    -0.63
     Crimea
    -0.62
    Es
    -0.62
    POSITIVE LOGITS
     riders
    1.18
     rider
    1.07
    hip
    1.03
    bike
    0.90
    chairs
    0.83
    accompan
    0.78
     ridden
    0.76
    illac
    0.76
    ngth
    0.73
    cript
    0.72
    Activations Density 0.008%

    No Known Activations