© 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. 1-RES-JB
    11. 413
    Prev
    Next
    INDEX
    Explanations

    phrases related to opting or choosing not to participate

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "outs" or "outsourcing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scotia
    -0.75
     Gemini
    -0.72
     litter
    -0.69
     Puzzles
    -0.68
     Grind
    -0.67
     Invalid
    -0.67
     Albion
    -0.67
     Meridian
    -0.65
     Panther
    -0.65
     Met
    -0.64
    POSITIVE LOGITS
     outs
    1.49
    ourced
    1.19
     Outs
    1.09
    terness
    0.92
    ourcing
    0.92
    chwitz
    0.87
    iders
    0.86
    chool
    0.83
    pec
    0.83
    sembly
    0.81
    Activations Density 0.002%

    No Known Activations