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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 15518
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "AG" followed by a number, potentially related to various topics or organizations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "AG" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stead
    -0.70
    pper
    -0.69
    days
    -0.63
     911
    -0.62
     fluids
    -0.61
     Jenner
    -0.59
     pepper
    -0.59
     Medicine
    -0.58
     patient
    -0.58
     Heck
    -0.57
    POSITIVE LOGITS
    allery
    1.10
    reement
    1.07
    AIN
    1.00
    uild
    1.00
    RIC
    1.00
    glomer
    0.99
    reements
    0.98
    EMENT
    0.95
    rowth
    0.94
    roup
    0.94
    Activations Density 0.006%

    No Known Activations