© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 18579
    Prev
    Next
    INDEX
    Explanations

    pronouns denoting people

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in a professional context

    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
     bothering
    -0.70
     pregn
    -0.69
     dstg
    -0.68
    Requ
    -0.65
     necessities
    -0.65
    Translation
    -0.63
    Failure
    -0.61
    proxy
    -0.60
     heartbeat
    -0.60
     coughing
    -0.60
    POSITIVE LOGITS
     graduated
    1.25
     oversaw
    1.13
     authored
    1.10
     joined
    1.10
     founded
    1.09
     attended
    1.08
     participated
    1.08
     served
    1.07
     specializes
    1.04
     chaired
    1.04
    Activations Density 0.175%

    No Known Activations