© 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. 0-RES-JB
    11. 6430
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the city "Varanasi."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Varanasi."

    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
    ione
    -0.75
    ãĥ©ãĥ³
    -0.70
    dash
    -0.66
     masturb
    -0.66
     censorship
    -0.65
     pedals
    -0.63
    gee
    -0.61
    anking
    -0.61
    HEAD
    -0.61
     franchise
    -0.61
    POSITIVE LOGITS
     Var
    3.97
    Var
    2.67
     var
    1.47
    var
    1.35
     Dim
    1.08
     Sv
    1.08
     Arn
    1.07
     Vor
    1.05
     Trin
    1.02
     Yan
    1.01
    Activations Density 0.024%

    No Known Activations