Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 13362
    Prev
    Next
    INDEX
    Explanations

    locations or places related to a specific city

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of San Jose or cities starting with "San"

    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
    theless
    -0.75
    ilater
    -0.71
    llor
    -0.71
    ï¸ı
    -0.68
    xual
    -0.68
    mercial
    -0.63
    llers
    -0.63
    anwhile
    -0.63
     numbering
    -0.63
     Wink
    -0.61
    POSITIVE LOGITS
    San
    1.14
     Francisco
    1.10
     Diego
    1.04
    ctuary
    1.01
     Antonio
    0.98
    ibel
    0.94
    gha
    0.93
    ction
    0.93
    itary
    0.92
    Disk
    0.90
    Activations Density 0.020%

    No Known Activations