© 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. 21135
    Prev
    Next
    INDEX
    Explanations

    language related to discussing and reporting various kinds of information or activities

    oai_token-act-pair · gpt-3.5-turbo

    significant terms and phrases related to evidence and accountability

    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
     anyways
    -0.63
    +.
    -0.63
     respectively
    -0.58
     themselves
    -0.55
     anyway
    -0.54
     scen
    -0.52
     shenan
    -0.52
    FTWARE
    -0.51
    itton
    -0.50
    ullivan
    -0.48
    POSITIVE LOGITS
     is
    1.32
     represents
    1.31
     refers
    1.30
     has
    1.28
     belongs
    1.28
     denotes
    1.27
     reflects
    1.27
     comprises
    1.27
     consists
    1.25
     constitutes
    1.25
    Activations Density 0.566%

    No Known Activations