© 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. 9-RES-JB
    11. 9861
    Prev
    Next
    INDEX
    Explanations

    references to All-Star athletes

    oai_token-act-pair · gpt-3.5-turbo

    references to "All-Star" awards or selections in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •All the Features!

    No Comments

    Negative Logits
     surrog
    -0.63
     sidel
    -0.62
     tremend
    -0.61
     disg
    -0.60
     recons
    -0.59
     reverse
    -0.59
    aminer
    -0.59
     separat
    -0.59
     tel
    -0.59
     slowing
    -0.58
    POSITIVE LOGITS
    ocation
    1.28
    igator
    1.22
    iances
    1.17
    ergy
    1.08
    ocated
    1.07
    iance
    1.07
    ocate
    1.06
    ergic
    1.06
    owed
    1.06
    winner
    1.06
    Activations Density 0.028%

    No Known Activations