© 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. 4334
    Prev
    Next
    INDEX
    Explanations

    specific verbs related to communication and information sharing

    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
     Sierra
    -0.56
     occupancy
    -0.54
     Milky
    -0.54
    orio
    -0.54
    keys
    -0.52
     Colo
    -0.52
     recovery
    -0.51
    ardo
    -0.51
    cession
    -0.51
    cot
    -0.51
    POSITIVE LOGITS
     aloud
    1.21
     extensively
    0.97
     elsewhere
    0.95
     prominently
    0.91
     herein
    0.91
     therein
    0.86
     by
    0.84
     explicitly
    0.78
    escription
    0.78
     sarcast
    0.76
    Activations Density 0.218%

    No Known Activations