© 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. 21172
    Prev
    Next
    INDEX
    Explanations

    comparisons between quantities, characteristics, or actions

    oai_token-act-pair · gpt-3.5-turbo

    comparative statements regarding various topics, focusing on contrasting entities or conditions

    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
     awa
    -0.63
    Topics
    -0.59
    afety
    -0.56
    details
    -0.56
    Topic
    -0.55
    escription
    -0.54
    later
    -0.53
     kindred
    -0.51
    ={
    -0.51
    uish
    -0.50
    POSITIVE LOGITS
     combined
    1.16
     did
    1.01
     does
    0.94
     ever
    0.94
     realizes
    0.84
     EVER
    0.84
     suggests
    0.81
    did
    0.80
     nor
    0.80
     counterparts
    0.80
    Activations Density 0.320%

    No Known Activations