© 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. 9586
    Prev
    Next
    INDEX
    Explanations

    Russian Cyrillic characters and numerical patterns

    oai_token-act-pair · gpt-3.5-turbo

    characters or elements from a non-Latin script or encoding

    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
    natureconservancy
    -0.69
    ixtures
    -0.58
    é¾įåĸļ士
    -0.57
    retty
    -0.54
     Occupations
    -0.54
    Weather
    -0.53
    amily
    -0.52
    itivity
    -0.52
    ertain
    -0.52
    sein
    -0.52
    POSITIVE LOGITS
    ĪĴ
    0.65
    otom
    0.62
     stroke
    0.60
     choke
    0.56
     (âĪĴ
    0.55
    otomy
    0.52
     Conc
    0.52
     Russo
    0.51
     deletion
    0.51
     wedge
    0.50
    Activations Density 1.160%

    No Known Activations