© 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. 6-RES-JB
    11. 9573
    Prev
    Next
    INDEX
    Explanations

    locations or places named "St." or "St" followed by a specific word

    oai_token-act-pair · gpt-3.5-turbo

    references to locations, specifically streets or cities

    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
    EStream
    -0.80
     "$:/
    -0.77
    ļéĨĴ
    -0.72
    merce
    -0.70
     GOODMAN
    -0.69
    hower
    -0.67
    hound
    -0.66
     Leilan
    -0.62
    DragonMagazine
    -0.62
    ption
    -0.60
    POSITIVE LOGITS
    rict
    1.16
    ocking
    1.11
    amps
    1.09
    amped
    1.09
    ealing
    1.08
    okes
    1.08
    alker
    1.08
    uffed
    1.05
    ills
    1.05
    oppable
    1.04
    Activations Density 0.029%

    No Known Activations