© 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. 20715
    Prev
    Next
    INDEX
    Explanations

    locations or addresses with specific street names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific streets and avenues

    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
    sonian
    -0.88
    orian
    -0.74
    berman
    -0.74
    MER
    -0.73
    arious
    -0.73
    ivated
    -0.71
    orius
    -0.71
    =-=-=-=-=-=-=-=-
    -0.70
    ERAL
    -0.70
    orians
    -0.70
    POSITIVE LOGITS
     Avenue
    0.98
     Rd
    0.87
     Corridor
    0.84
     Parkway
    0.84
     Extension
    0.83
     Route
    0.83
     Tunnel
    0.82
     Junction
    0.82
     Blvd
    0.79
     NW
    0.79
    Activations Density 0.032%

    No Known Activations