© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 14370
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or tasks that need to be performed or decisions that need to be made

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating possession or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     externalToEVAOnly
    -0.70
    ught
    -0.67
    existent
    -0.66
    ruff
    -0.59
     civilizations
    -0.58
    gary
    -0.57
    hetic
    -0.57
     miscar
    -0.57
     hurts
    -0.57
    alias
    -0.55
    POSITIVE LOGITS
     ample
    1.09
     latitude
    1.06
     discretion
    0.98
     until
    0.97
     flexibility
    0.95
     plenty
    0.90
     access
    0.89
     opportunity
    0.86
    ample
    0.86
     jurisdiction
    0.85
    Activations Density 0.212%

    No Known Activations