© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RES-JB
    11. 8897
    Prev
    Next
    INDEX
    Explanations

    characters from a variety of languages, potentially indicating multilingual content

    oai_token-act-pair · gpt-3.5-turbo

    items with specific characteristic patterns or representations, likely relating to a particular language or encoding system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clover
    -0.84
    essa
    -0.78
    ouble
    -0.75
    ierrez
    -0.73
    esville
    -0.73
    arton
    -0.72
    onomy
    -0.71
     GOODMAN
    -0.71
    ivating
    -0.69
    assador
    -0.69
    POSITIVE LOGITS
    Ñ
    1.56
    ÑĤ
    1.52
    ÑĢ
    1.52
    Ñģ
    1.45
    е
    1.41
    н
    1.38
    Ñı
    1.35
    Ð
    1.34
    к
    1.32
    д
    1.31
    Activations Density 0.015%

    No Known Activations