© 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. 6-RES-JB
    11. 11854
    Prev
    Next
    INDEX
    Explanations

    the word "Mail"

    oai_token-act-pair · gpt-3.5-turbo

    references to the publication "Mail."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sqor
    -0.76
    osed
    -0.74
    razil
    -0.73
    oken
    -0.69
    structed
    -0.68
    iscopal
    -0.67
    issan
    -0.67
    inant
    -0.66
    essential
    -0.65
    umbers
    -0.64
    POSITIVE LOGITS
    bag
    1.13
    bags
    1.02
     Online
    0.93
     Mail
    0.87
    boxes
    0.84
    Online
    0.84
    ing
    0.83
    Mail
    0.81
    box
    0.80
    biz
    0.80
    Activations Density 0.009%

    No Known Activations