© 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. 22962
    Prev
    Next
    INDEX
    Explanations

    words or sequences of characters in Cyrillic script

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols from specific non-Latin alphabets and languages

    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
    soType
    -0.77
    natureconservancy
    -0.68
    helle
    -0.68
    isSpecialOrderable
    -0.63
    amia
    -0.63
    bnb
    -0.62
    utical
    -0.62
    entary
    -0.60
    giene
    -0.59
    igans
    -0.58
    POSITIVE LOGITS
    Ö¼
    0.65
     Vaugh
    0.61
     Niet
    0.57
     combustion
    0.56
     Kenobi
    0.54
     Divide
    0.54
     (âĪĴ
    0.53
    bush
    0.53
    ĪĴ
    0.52
     coli
    0.52
    Activations Density 1.205%

    No Known Activations