© 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. 8-RES-JB
    11. 1165
    Prev
    Next
    INDEX
    Explanations

    a mix of characters and possibly specific words or phrases that seem to not have a clear thematic link

    oai_token-act-pair · gpt-3.5-turbo

    non-standard and 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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ettings
    -0.80
     tremend
    -0.76
    yip
    -0.75
    eatures
    -0.64
     Grimes
    -0.64
    olean
    -0.62
    ottesville
    -0.62
    wana
    -0.60
    hib
    -0.60
     Wyr
    -0.60
    POSITIVE LOGITS
    ë
    0.78
    à¤
    0.75
    ÑĤ
    0.73
    ì
    0.73
    à¸
    0.72
    ìĿ
    0.72
    inen
    0.71
    talk
    0.70
    ãģ£
    0.69
    ëĭ
    0.68
    Activations Density 0.043%

    No Known Activations