© 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. 0-RES-JB
    11. 13932
    Prev
    Next
    INDEX
    Explanations

    mentions of government agencies and legal matters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the abbreviation "SL" that likely refer to "national security letters" or related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fortune
    -0.78
    ð
    -0.75
    ocrates
    -0.71
    endi
    -0.71
    frey
    -0.70
    unes
    -0.69
    Pokémon
    -0.67
    oÄŁ
    -0.66
     Ezek
    -0.66
     psychiat
    -0.66
    POSITIVE LOGITS
     SL
    3.45
    SL
    3.00
     DSL
    1.42
     SO
    1.41
     RL
    1.39
     LS
    1.36
     Sl
    1.35
    sl
    1.30
     SC
    1.26
     SP
    1.22
    Activations Density 0.025%

    No Known Activations