© 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. 4-RES-JB
    11. 4880
    Prev
    Next
    INDEX
    Explanations

    activities related to sending and receiving text messages

    oai_token-act-pair · gpt-3.5-turbo

    references to texting and text messages

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

    No Comments

    Negative Logits
    vre
    -0.71
    arte
    -0.71
    vernment
    -0.70
    liga
    -0.69
    ulic
    -0.68
    pure
    -0.67
    Bir
    -0.67
     Flavoring
    -0.66
    ritis
    -0.65
    Marginal
    -0.65
    POSITIVE LOGITS
     messages
    1.20
     texting
    1.05
     messaging
    1.04
    message
    0.99
     message
    0.97
     Messages
    0.95
     texted
    0.90
     reminders
    0.86
    ured
    0.85
    email
    0.84
    Activations Density 0.042%

    No Known Activations