© 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. 9-RES-JB
    11. 4284
    Prev
    Next
    INDEX
    Explanations

    patterned sequences with special characters

    oai_token-act-pair · gpt-3.5-turbo
    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
     Droid
    -0.58
     Libyan
    -0.56
     Kenyan
    -0.52
     relay
    -0.52
     blacklist
    -0.52
     scattering
    -0.51
     rom
    -0.50
     board
    -0.50
     limitation
    -0.50
     bounty
    -0.50
    POSITIVE LOGITS
    ¹
    1.06
    Į
    0.91
    ¢
    0.88
    ²
    0.87
    ı
    0.87
    ¬
    0.86
    ¡
    0.86
    Ĵ
    0.85
    £
    0.84
    ł
    0.83
    Activations Density 0.375%

    No Known Activations