© 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. 23563
    Prev
    Next
    INDEX
    Explanations

    dialogue where characters are asking questions or making statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with dialogue or conversations

    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
     fres
    -0.77
    MpServer
    -0.73
     ideal
    -0.68
     vaccinations
    -0.67
     orphans
    -0.65
     vaccinated
    -0.64
    etheless
    -0.64
     travelling
    -0.64
     moder
    -0.62
     fermented
    -0.62
    POSITIVE LOGITS
    Suddenly
    1.05
    Again
    0.99
    Everyone
    0.94
    Pause
    0.91
    Fuck
    0.88
    XXX
    0.88
    Huh
    0.87
    Then
    0.87
    Hmm
    0.87
    "-
    0.86
    Activations Density 0.277%

    No Known Activations