© 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. 3-RES-JB
    11. 23354
    Prev
    Next
    INDEX
    Explanations

    words related to mail delivery

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "mail" and its related contexts

    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
     Durham
    -0.68
    oulos
    -0.66
     ESV
    -0.65
     LORD
    -0.63
    Jer
    -0.63
     Democr
    -0.63
    ETF
    -0.62
    aughs
    -0.62
    nen
    -0.61
     whiff
    -0.60
    POSITIVE LOGITS
    boxes
    1.38
    bag
    1.26
     mail
    1.23
    bags
    1.11
     mailbox
    0.99
    box
    0.97
    email
    0.95
    mail
    0.94
     inbox
    0.89
     exch
    0.86
    Activations Density 0.010%

    No Known Activations