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. 12-RES-JB
    6. 6979
    Prev
    Next
    INDEX
    Explanations

    phrases related to community development and construction projects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of the word "there" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IPM
    -0.71
     Shap
    -0.57
     Azerb
    -0.56
    ãĥ¼ãĥĨ
    -0.56
     Order
    -0.54
     Bulgar
    -0.53
     Tome
    -0.53
     Gaul
    -0.52
     Luxem
    -0.52
     Kirin
    -0.51
    POSITIVE LOGITS
     aren
    1.14
     weren
    1.10
     ain
    1.09
    's
    1.07
     hasn
    1.07
     shouldn
    1.04
     are
    1.03
     wasn
    1.02
    're
    0.99
     needs
    0.98
    Activations Density 0.126%

    No Known Activations