© 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. 19036
    Prev
    Next
    INDEX
    Explanations

    technical terms related to connectivity or infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    connections and relationships between different concepts or entities

    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
    amous
    -0.69
    kish
    -0.66
    ãĥ´ãĤ¡
    -0.66
    ritical
    -0.66
    yss
    -0.65
    Ô
    -0.63
    orous
    -0.62
    onomous
    -0.61
    independent
    -0.60
    usable
    -0.60
    POSITIVE LOGITS
     Ltd
    0.78
     Initiative
    0.76
    naire
    0.74
     Generator
    0.72
     LLP
    0.71
     LTD
    0.69
     Program
    0.68
     Facility
    0.66
     Association
    0.65
     Competition
    0.64
    Activations Density 0.565%

    No Known Activations