© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 16324
    Prev
    Next
    INDEX
    Explanations

    references to the city of San Francisco

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "San Francisco."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inner
    -0.66
    stock
    -0.65
     skirts
    -0.64
     intrins
    -0.61
     Xbox
    -0.60
    sk
    -0.58
     Cyn
    -0.58
     cull
    -0.57
    Ark
    -0.57
     stuffing
    -0.57
    POSITIVE LOGITS
     Francisco
    3.41
     Diego
    2.10
     Jose
    1.75
     José
    1.68
     Pedro
    1.66
    Franc
    1.64
     Antonio
    1.57
     Fernando
    1.52
     Julio
    1.50
     Pablo
    1.50
    Activations Density 0.020%

    No Known Activations