© 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. 21654
    Prev
    Next
    INDEX
    Explanations

    unique email addresses

    oai_token-act-pair · gpt-3.5-turbo

    references to email addresses and related email concepts

    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
    TRY
    -0.78
    Jer
    -0.75
    jury
    -0.75
    liga
    -0.73
    045
    -0.72
    OV
    -0.69
    ãĥķãĤ©
    -0.69
    ICLE
    -0.68
    anu
    -0.66
    lust
    -0.65
    POSITIVE LOGITS
     inbox
    1.19
     address
    1.11
     addresses
    1.07
     correspondence
    0.98
    address
    0.94
     messages
    0.90
     newsletters
    0.90
     Address
    0.88
    email
    0.85
     exchanges
    0.85
    Activations Density 0.041%

    No Known Activations