© 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. 6-RES-JB
    11. 9148
    Prev
    Next
    INDEX
    Explanations

    technical specifications and descriptions of electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of technological products and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apo
    -0.62
     advis
    -0.58
     consulate
    -0.58
     withdrawals
    -0.57
    ļéĨĴ
    -0.57
    endment
    -0.57
    administ
    -0.56
    hower
    -0.56
     Emails
    -0.55
     withdrawal
    -0.54
    POSITIVE LOGITS
     genre
    0.87
     legendary
    0.70
     showcase
    0.70
     indie
    0.69
     fanbase
    0.69
     genres
    0.68
     futuristic
    0.68
     customizable
    0.68
     versatile
    0.68
     stylish
    0.68
    Activations Density 1.944%

    No Known Activations