© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 13712
    Prev
    Next
    INDEX
    Explanations

    references to news articles by the Associated Press (AP)

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the acronym "AP," likely indicating the Associated Press as a news source

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĬ
    -0.66
    lords
    -0.65
     Lords
    -0.65
    ãĥĥãĥī
    -0.65
    chest
    -0.64
     Jenner
    -0.64
    ãĤ¬
    -0.63
    pron
    -0.62
     Luthor
    -0.62
    ãĤ¹ãĥĪ
    -0.62
    POSITIVE LOGITS
    PLIED
    1.24
    AP
    1.03
    PLE
    0.96
    vantage
    0.95
    ascal
    0.93
    PLIC
    0.92
    PAR
    0.91
    insula
    0.89
    sburg
    0.87
    ollo
    0.83
    Activations Density 0.007%

    No Known Activations