© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11035
    Prev
    Next
    INDEX
    Explanations

    references to a specific publication called "Mail" or "Daily Mail"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Mail" publication

    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
    razil
    -0.69
     HRC
    -0.67
    structed
    -0.65
     LORD
    -0.63
    cffffcc
    -0.62
    ORN
    -0.60
    osed
    -0.60
    sem
    -0.60
    itol
    -0.60
    judicial
    -0.60
    POSITIVE LOGITS
    bag
    1.18
    bags
    1.06
     Mail
    1.01
    Mail
    0.97
    mail
    0.91
    ing
    0.85
    boxes
    0.81
     Online
    0.81
     Tycoon
    0.79
    legram
    0.77
    Activations Density 0.008%

    No Known Activations