© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 10274
    Prev
    Next
    INDEX
    Explanations

    email-related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to email communication and its associated metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ãĤ¦ãĤ¹
    -0.97
    女
    -0.88
    natureconservancy
    -0.84
    ãĤ´ãĥ³
    -0.77
     pione
    -0.75
    vation
    -0.73
    ãĤ¹ãĥĪ
    -0.72
    owell
    -0.72
     rul
    -0.72
     proverb
    -0.71
    POSITIVE LOGITS
     subsidiaries
    1.00
     entities
    0.90
     deceased
    0.90
     unidentified
    0.89
     persons
    0.88
     subscribers
    0.86
     individuals
    0.85
     clients
    0.84
     accounts
    0.84
     customers
    0.83
    Activations Density 0.352%

    No Known Activations