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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 14582
    Prev
    Next
    INDEX
    Explanations

    text related to news articles or press releases, particularly those containing the abbreviation "AP."

    oai_token-act-pair · gpt-3.5-turbo

    references to the Associated Press (AP) news agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     revolving
    -0.73
     Cod
    -0.66
     teeth
    -0.66
     trout
    -0.65
    ness
    -0.64
     bowel
    -0.64
     Darth
    -0.63
     nobles
    -0.63
     ladies
    -0.63
     Sith
    -0.62
    POSITIVE LOGITS
    AP
    4.02
    APS
    2.42
     AP
    1.99
    APP
    1.92
    APE
    1.81
    ap
    1.78
    Reuters
    1.70
    APH
    1.65
    Associated
    1.58
    AFP
    1.55
    Activations Density 0.015%

    No Known Activations