© 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. 9-RES-JB
    11. 18420
    Prev
    Next
    INDEX
    Explanations

    strings of characters that are likely encoding errors or data corruption, comprised of characters that are not typical in natural language text

    oai_token-act-pair · gpt-3.5-turbo

    non-standard or special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -1.03
     decomp
    -0.73
    schild
    -0.70
     guiActiveUnfocused
    -0.66
    bucks
    -0.65
    creen
    -0.65
     kne
    -0.63
     nexus
    -0.62
    ifications
    -0.60
     excluding
    -0.60
    POSITIVE LOGITS
    ģ
    1.54
    ĺ
    1.49
    ĵ
    1.45
    Ĩ
    1.44
    ļ
    1.39
    ¢
    1.38
    ½
    1.38
    ²
    1.36
    ĭ
    1.36
    ¤
    1.35
    Activations Density 0.031%

    No Known Activations