Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 4104
    Prev
    Next
    INDEX
    Explanations

    references to numerical information, including rates, dates, and measurements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wraps
    -0.58
    guyen
    -0.50
     grievances
    -0.50
    inness
    -0.48
     memos
    -0.48
     playbook
    -0.47
     rumours
    -0.45
     sails
    -0.45
     bells
    -0.45
     detrim
    -0.44
    POSITIVE LOGITS
    .[
    1.06
    .(
    1.04
    .<
    1.03
    .
    1.02
    .*
    1.00
    .</
    0.96
    *.
    0.95
    .?
    0.94
    _.
    0.93
    .�
    0.92
    Activations Density 0.864%

    No Known Activations