© 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 EvalsExportsAPI 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. 14866
    Prev
    Next
    INDEX
    Explanations

    mentions that emphasize actions or events

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations, agencies, and systemic structures involved in governance or societal issues

    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
    etheless
    -0.87
    ãĤ´ãĥ³
    -0.83
     looph
    -0.69
     "#
    -0.69
    arnaev
    -0.65
     Amid
    -0.65
     Alas
    -0.62
     §§
    -0.62
    Amid
    -0.62
     Yet
    -0.62
    POSITIVE LOGITS
     really
    1.09
     [
    1.08
     kind
    1.08
     hasn
    1.07
     basically
    1.07
     doesn
    1.05
     ...
    1.01
     understands
    0.99
     wants
    0.98
     everybody
    0.98
    Activations Density 0.426%

    No Known Activations