© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 15308
    Prev
    Next
    INDEX
    Explanations

    references to subway systems with a strong emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to subway systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    manship
    -0.76
     Williamson
    -0.74
    ores
    -0.70
    Var
    -0.69
    mal
    -0.68
     Bret
    -0.66
     Hardy
    -0.63
     Mal
    -0.63
    nat
    -0.62
     Tyr
    -0.61
    POSITIVE LOGITS
     subway
    3.58
     Subway
    2.26
     MTA
    1.96
     TTC
    1.93
     streetcar
    1.90
     metro
    1.65
     BART
    1.53
     Amtrak
    1.48
     Tube
    1.45
     freeway
    1.41
    Activations Density 0.018%

    No Known Activations