© 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 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. 2-RES-JB
    11. 541
    Prev
    Next
    INDEX
    Explanations

    email-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    the word "email."

    oai_token-act-pair · gpt-4-turbo

    mentions of the word "email."

    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
    ICLE
    -0.79
    045
    -0.79
    TRY
    -0.77
    ETF
    -0.70
    NEY
    -0.70
    GBT
    -0.69
    BP
    -0.68
    Jer
    -0.68
    033
    -0.64
     Pf
    -0.64
    POSITIVE LOGITS
     inbox
    1.09
     address
    1.00
     addresses
    0.96
    email
    0.95
     email
    0.93
    address
    0.83
     correspondence
    0.82
    mail
    0.82
    bag
    0.81
     newsletters
    0.79
    Activations Density 0.022%

    No Known Activations