© 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. 7-RES-JB
    11. 2246
    Prev
    Next
    INDEX
    Explanations

    email subject lines

    oai_token-act-pair · gpt-3.5-turbo

    email-related content and timestamps in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     temples
    -0.97
     Saga
    -0.76
     meter
    -0.75
     Kard
    -0.68
     Aether
    -0.68
     biome
    -0.68
     saves
    -0.68
     Underworld
    -0.66
     gameplay
    -0.66
     animations
    -0.66
    POSITIVE LOGITS
    olicited
    1.02
    Message
    0.99
     Abedin
    0.95
    Dear
    0.94
     UNCLASSIFIED
    0.93
     forwarded
    0.92
    Mail
    0.86
    mail
    0.85
    reply
    0.85
    Date
    0.83
    Activations Density 0.220%

    No Known Activations