© 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. 2262
    Prev
    Next
    INDEX
    Explanations

    phrases expressing positive feelings or sentiments

    oai_token-act-pair · gpt-3.5-turbo
    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
    ume
    -0.69
     improperly
    -0.68
    omy
    -0.65
     inappropriately
    -0.65
    uyomi
    -0.65
    Downloadha
    -0.65
     detrimental
    -0.64
     unworthy
    -0.63
    bands
    -0.62
    cessive
    -0.62
    POSITIVE LOGITS
     comrade
    0.79
    Congratulations
    0.78
     congr
    0.77
     reassured
    0.75
     Announce
    0.73
     tid
    0.71
     finally
    0.70
     luck
    0.70
    noon
    0.70
    reen
    0.68
    Activations Density 0.262%

    No Known Activations