© 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
    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. 18558
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate generalizations or normative statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to general statements or introductions, typically starting with "Generally" or "Initially"

    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
    ggles
    -0.79
    aily
    -0.77
    kamp
    -0.74
    kefeller
    -0.71
    ocaust
    -0.66
    addons
    -0.65
    umbn
    -0.65
    "},"
    -0.63
    natureconservancy
    -0.63
    uras
    -0.62
    POSITIVE LOGITS
     speaking
    1.16
    adays
    0.90
    ,
    0.88
     there
    0.87
     we
    0.80
     they
    0.78
     it
    0.77
    ,.
    0.75
     Speaking
    0.74
    speaking
    0.70
    Activations Density 0.173%

    No Known Activations