© 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. 4-RES-JB
    11. 10506
    Prev
    Next
    INDEX
    Explanations

    lines that include symbols related to coding or text formatting

    oai_token-act-pair · gpt-3.5-turbo

    symbols or special characters often used in informal or digital communication

    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
     scattering
    -0.78
     scatter
    -0.72
     dust
    -0.67
     zoning
    -0.66
    ensical
    -0.64
     wind
    -0.63
     monop
    -0.63
    itably
    -0.63
     stagger
    -0.62
    iliary
    -0.62
    POSITIVE LOGITS
    ¹
    1.15
    º
    1.00
    Į
    0.95
    į
    0.93
    »
    0.93
    £
    0.92
    ¼
    0.85
    ¬
    0.84
    §
    0.84
    ²
    0.84
    Activations Density 0.720%

    No Known Activations