© 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 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. 11-RES-JB
    11. 14920
    Prev
    Next
    INDEX
    Explanations

    references to legal, ethical, or moral rights

    oai_token-act-pair · gpt-3.5-turbo

    words related to rights, emphasizing their importance and implications for various groups

    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
    ergy
    -0.71
    ravis
    -0.66
     combust
    -0.65
    asty
    -0.64
     Sark
    -0.64
     Solitaire
    -0.63
    ools
    -0.60
    Lens
    -0.57
     Claus
    -0.57
     pollen
    -0.57
    POSITIVE LOGITS
     holders
    1.09
     conferred
    0.98
     afforded
    0.97
     holder
    0.97
     guaranteed
    0.96
     Granted
    0.96
    ignty
    0.96
     granted
    0.94
    holders
    0.94
    holder
    0.93
    Activations Density 0.054%

    No Known Activations