© 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. 11-RES-JB
    11. 21150
    Prev
    Next
    INDEX
    Explanations

    names of technology companies and individuals working in the tech industry

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and brand names related to electronics and computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lightly
    -0.55
     starting
    -0.52
     following
    -0.51
     quickly
    -0.50
    âĢİ
    -0.50
     completely
    -0.49
     gradually
    -0.49
     sufficiently
    -0.49
     drastically
    -0.49
     naturally
    -0.49
    POSITIVE LOGITS
    ullivan
    0.63
    çĶ°
    0.61
    itto
    0.56
     TBA
    0.55
    ĪĴ
    0.55
    negie
    0.53
     respectively
    0.53
    ikuman
    0.52
    imental
    0.51
     etc
    0.50
    Activations Density 1.166%

    No Known Activations