© 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. 9-RES-JB
    11. 15815
    Prev
    Next
    INDEX
    Explanations

    prompts asking for feedback or engagement from the audience

    oai_token-act-pair · gpt-3.5-turbo

    requests for feedback and communication from readers

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.87
    RAY
    -0.62
    cffffcc
    -0.62
    ा
    -0.61
    à¦
    -0.61
    ãĥ£
    -0.61
    FactoryReloaded
    -0.60
    hift
    -0.60
    ADD
    -0.58
    ARI
    -0.58
    POSITIVE LOGITS
     Spons
    0.79
     Email
    0.76
     Feedback
    0.72
     ASAP
    0.72
     feedback
    0.62
     info
    0.62
     beforehand
    0.61
    Email
    0.61
     Bleach
    0.61
     newsletter
    0.61
    Activations Density 0.064%

    No Known Activations