© 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
    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. 24305
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "riders"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "riders" in various contexts related to transportation or transit

    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
    rontal
    -0.81
    opath
    -0.76
    orial
    -0.73
    argon
    -0.73
    aples
    -0.70
     pear
    -0.69
    ertain
    -0.68
    osis
    -0.66
    urated
    -0.65
    otic
    -0.64
    POSITIVE LOGITS
     riders
    1.44
     rider
    1.30
    bike
    0.98
    hip
    0.94
     Riders
    0.87
     ridden
    0.85
    rider
    0.83
     fares
    0.80
     ride
    0.76
    ngth
    0.76
    Activations Density 0.010%

    No Known Activations