© 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. 9238
    Prev
    Next
    INDEX
    Explanations

    terminology related to programming and technology, such as programming languages, coding practices, and system components

    oai_token-act-pair · gpt-3.5-turbo

    terms related to systems, connections, and organization in various contexts

    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
    angelo
    -0.79
    ufact
    -0.71
    avorite
    -0.70
    ©¶æ¥µ
    -0.66
    PDATE
    -0.65
    ãĤ¢ãĥ«
    -0.64
    owe
    -0.64
    76561
    -0.63
    ij士
    -0.61
    rake
    -0.61
    POSITIVE LOGITS
     Dialogue
    0.59
     motions
    0.57
     Pv
    0.57
    apters
    0.55
     folders
    0.55
     Perception
    0.52
    ourses
    0.52
    isively
    0.51
     modes
    0.51
     poles
    0.50
    Activations Density 1.165%

    No Known Activations