© 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. 10-RES-JB
    11. 4387
    Prev
    Next
    INDEX
    Explanations

    words related to the Arabic or Berber languages

    oai_token-act-pair · gpt-3.5-turbo

    references to the character "Amiibo" and its related features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.75
     Sloven
    -0.64
    writers
    -0.62
    é»Ĵ
    -0.61
    00007
    -0.58
     Romania
    -0.57
     Croatian
    -0.55
     datas
    -0.55
    ï¸ı
    -0.55
     circles
    -0.55
    POSITIVE LOGITS
    assador
    1.03
    ICAN
    0.89
    ixture
    0.87
    anwhile
    0.85
    ibo
    0.85
    illin
    0.78
    lehem
    0.77
    athering
    0.77
    EMENT
    0.76
    akeru
    0.76
    Activations Density 0.056%

    No Known Activations