© 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. 1-RES-JB
    11. 14586
    Prev
    Next
    INDEX
    Explanations

    references to pedestrian-related objects or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to pedestrians and pedestrian-related topics

    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
    ARA
    -0.66
    outube
    -0.65
     marrow
    -0.65
    alin
    -0.64
    RAM
    -0.64
    rex
    -0.64
    zona
    -0.63
    ATCH
    -0.63
    OUNT
    -0.63
    rador
    -0.63
    POSITIVE LOGITS
     pedestrian
    1.18
     pedestrians
    1.06
     sidewalks
    0.80
    walk
    0.78
    istani
    0.75
    kees
    0.74
     crossings
    0.73
    NetMessage
    0.69
     malls
    0.69
    imer
    0.67
    Activations Density 0.009%

    No Known Activations