© 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. 3-RES-JB
    6. 6262
    Prev
    Next
    INDEX
    Explanations

    mentions of the news agency "REUTERS" in document captions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "REUTERS."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.74
    ebook
    -0.70
    axe
    -0.70
    hma
    -0.69
    pired
    -0.68
    izers
    -0.66
    owder
    -0.64
    lain
    -0.63
    ysis
    -0.62
    ount
    -0.61
    POSITIVE LOGITS
     REUTERS
    1.08
    UTERS
    0.89
    externalActionCode
    0.86
    CLASSIFIED
    0.86
    PLIC
    0.82
     PHOTO
    0.81
     ANGEL
    0.79
    Film
    0.75
     srfAttach
    0.74
    AMI
    0.73
    Activations Density 0.008%

    No Known Activations