© 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. 9-RES-JB
    11. 11250
    Prev
    Next
    INDEX
    Explanations

    specific locations within a city

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REP
    -0.74
    =-=-=-=-=-=-=-=-
    -0.72
     oblig
    -0.66
     indisp
    -0.66
    roid
    -0.65
    NSA
    -0.65
    imbabwe
    -0.64
    IAN
    -0.63
     reproduce
    -0.62
     submar
    -0.62
    POSITIVE LOGITS
     Avenue
    1.05
     Boulevard
    1.04
     Interstate
    1.03
     Canal
    0.97
     Highway
    0.95
     Blvd
    0.91
     Sunset
    0.91
     Ave
    0.90
     Rue
    0.90
     Broadway
    0.90
    Activations Density 0.049%

    No Known Activations