© 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. 9-RES-JB
    11. 16096
    Prev
    Next
    INDEX
    Explanations

    words that seem to have encoding errors, particularly related to the characters 'Â' and 'ĵ'

    oai_token-act-pair · gpt-3.5-turbo

    the symbol "Â" in various contexts

    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
    -0.94
     Nanto
    -0.80
    manship
    -0.70
    anwhile
    -0.70
    ãģ®éŃĶ
    -0.69
     comprehens
    -0.67
     Kamp
    -0.67
    iants
    -0.66
     Mamm
    -0.66
     VK
    -0.66
    POSITIVE LOGITS
    ´
    1.61
    ³
    1.54
    ¿
    1.51
    ¨
    1.50
    ¦
    1.49
    ¹
    1.47
    ¬
    1.41
    ¸
    1.40
    ¢
    1.39
    ¼
    1.39
    Activations Density 0.014%

    No Known Activations