© 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. 3-RES-JB
    11. 18265
    Prev
    Next
    INDEX
    Explanations

    words related to decorations or markings on objects

    oai_token-act-pair · gpt-3.5-turbo

    references to items or entities categorized as "als."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \\\\\\\\
    -0.88
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.86
    REP
    -0.78
     Stories
    -0.72
    hold
    -0.68
    SourceFile
    -0.68
    Column
    -0.67
    SPONSORED
    -0.64
    Solid
    -0.64
     constituent
    -0.62
    POSITIVE LOGITS
    mith
    1.19
    anguage
    1.04
    rals
    1.04
    uits
    0.99
    pace
    0.99
    ayer
    0.99
    urgical
    0.98
    ighting
    0.96
    uit
    0.94
    ibaba
    0.94
    Activations Density 0.020%

    No Known Activations