© 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. 10-RES-JB
    11. 18800
    Prev
    Next
    INDEX
    Explanations

    proper nouns and locations, specifically focusing on mentions of the location Tiraspol

    oai_token-act-pair · gpt-3.5-turbo

    suffixes or segments common in names and terms, particularly in a geographic or urban context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     judging
    -0.72
    WHERE
    -0.65
     determining
    -0.58
     distinguishing
    -0.58
     discriminating
    -0.58
    moderate
    -0.57
     fielding
    -0.56
     identifying
    -0.56
     sensitive
    -0.56
     additive
    -0.55
    POSITIVE LOGITS
    utra
    1.19
    ierre
    1.03
    arthy
    1.02
    onte
    0.95
    augh
    0.92
    icz
    0.91
    ool
    0.90
    arte
    0.89
    ython
    0.89
    reek
    0.88
    Activations Density 0.102%

    No Known Activations