© 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. 6-RES-JB
    11. 17852
    Prev
    Next
    INDEX
    Explanations

    mentions of pedestrian-related topics, such as pedestrian safety, bridges, fencing, collisions, and connections

    oai_token-act-pair · gpt-3.5-turbo

    references to pedestrian safety and related transportation issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     marrow
    -0.87
    mable
    -0.69
     Pharma
    -0.69
     Centauri
    -0.69
    berman
    -0.67
    zona
    -0.66
    resso
    -0.66
    xit
    -0.65
    resses
    -0.64
    outube
    -0.64
    POSITIVE LOGITS
     pedestrians
    0.94
     pedestrian
    0.77
    own
    0.74
     obstruction
    0.74
     obstruct
    0.73
     jog
    0.70
    mast
    0.70
     alley
    0.70
     crossings
    0.70
    walk
    0.70
    Activations Density 0.021%

    No Known Activations