© 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. 10-RES-JB
    11. 18589
    Prev
    Next
    INDEX
    Explanations

    email correspondence related to various individuals and organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of correspondence or communication, particularly emails and messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entimes
    -0.82
    cipline
    -0.72
    Synopsis
    -0.72
    ptions
    -0.71
    Interstitial
    -0.70
    merce
    -0.69
    wcsstore
    -0.68
    iencies
    -0.67
    endas
    -0.67
    meal
    -0.66
    POSITIVE LOGITS
     someone
    1.04
     somebody
    0.90
     unidentified
    0.88
     disgruntled
    0.83
     Jill
    0.81
     Valerie
    0.79
     Sharon
    0.79
     Diane
    0.78
     spokesperson
    0.78
     Assistant
    0.78
    Activations Density 0.118%

    No Known Activations