© 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. 5725
    Prev
    Next
    INDEX
    Explanations

    phrases related to monitoring and investigation

    oai_token-act-pair · gpt-3.5-turbo

    active expressions of monitoring or evaluating situations

    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
     300
    -0.73
    wine
    -0.72
    stones
    -0.69
     700
    -0.69
     4000
    -0.67
     3000
    -0.66
     2500
    -0.66
     1600
    -0.66
    rake
    -0.66
     780
    -0.66
    POSITIVE LOGITS
    âĢ
    1.72
     âĢ
    1.26
    ¨
    1.14
     âĶ
    1.11
    âľ
    1.10
     Â
    1.06
    âĢł
    1.03
    Â
    1.01
    âģ
    1.00
    Æ
    0.99
    Activations Density 2.621%

    No Known Activations