© 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. 12-RES-JB
    11. 4255
    Prev
    Next
    INDEX
    Explanations

    web URLs, TV channel broadcasts, and Linux commands

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    numerical data and likelihood expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    gone
    -0.41
    omnia
    -0.41
    ciplinary
    -0.41
    kus
    -0.41
    patient
    -0.40
    winning
    -0.40
    udence
    -0.40
    examination
    -0.40
    rament
    -0.39
    mort
    -0.38
    POSITIVE LOGITS
     Quote
    0.63
     ----------------------------------------------------------------
    0.62
    <|endoftext|>
    0.61
     =================================================================
    0.58
     Reply
    0.58
     Delete
    0.58
     =================================
    0.57
     Languages
    0.56
     Usage
    0.55
     --------------------------------
    0.54
    Activations Density 0.448%

    No Known Activations