© 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. 6-RES-JB
    11. 3589
    Prev
    Next
    INDEX
    Explanations

    locations described with street names and directions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations or addresses

    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
     abroad
    -0.82
    ouble
    -0.75
     stockp
    -0.74
     saliva
    -0.69
     overseas
    -0.68
    erity
    -0.67
    zees
    -0.66
     semen
    -0.66
    icter
    -0.66
    oyal
    -0.64
    POSITIVE LOGITS
     intersection
    1.12
     intersections
    1.00
     Boulevard
    1.00
     NW
    0.97
     Avenue
    0.96
     Blvd
    0.94
     Corridor
    0.88
     corridor
    0.88
     Plaza
    0.88
     Hyde
    0.86
    Activations Density 0.287%

    No Known Activations