© 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 EvalsExportsinterp-engineNEWAPI 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. 4259
    Prev
    Next
    INDEX
    Explanations

    words related to dialogue quotes with punctuation and conversational flow

    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
     vaccinations
    -0.71
    icultural
    -0.68
     fres
    -0.66
     donating
    -0.61
    sterdam
    -0.61
     restrooms
    -0.61
     travelling
    -0.61
     migration
    -0.60
     vaccinated
    -0.60
     aging
    -0.59
    POSITIVE LOGITS
    "-
    0.95
    Pause
    0.91
    Suddenly
    0.90
    Fuck
    0.86
     nodded
    0.85
    ³³³³³³³³
    0.83
    =-=-=-=-=-=-=-=-
    0.82
    "âĢ¦
    0.78
    ³³³
    0.77
    Alright
    0.77
    Activations Density 0.163%

    No Known Activations