© 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 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. 4-RES-JB
    11. 6959
    Prev
    Next
    INDEX
    Explanations

    Russian text containing the character "Ñ" in various positions

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols used in a specific encoding format

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

    No Comments

    Negative Logits
    enegger
    -0.78
    cliffe
    -0.73
     WARN
    -0.65
    anwhile
    -0.65
    ogene
    -0.64
    displayText
    -0.63
    butt
    -0.63
    nels
    -0.63
    trace
    -0.62
     Jem
    -0.62
    POSITIVE LOGITS
    ħ
    1.52
    ĩ
    1.45
    Ķ
    1.43
    ķ
    1.35
    İ
    1.31
    Ī
    1.30
    Ħ
    1.28
    Ĩ
    1.28
    ī
    1.27
    ĸ
    1.26
    Activations Density 0.006%

    No Known Activations