© 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. 12-RES-JB
    11. 2808
    Prev
    Next
    INDEX
    Explanations

    sentences related to personal reflections and societal observations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    emotions related to confusion or discomfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     challeng
    -0.80
     satell
    -0.75
     abduct
    -0.71
    undai
    -0.71
     torpedo
    -0.70
     bonded
    -0.70
     millenn
    -0.69
     staggered
    -0.69
     matured
    -0.69
     discern
    -0.68
    POSITIVE LOGITS
    âĢ
    1.75
     âĢ
    1.37
    âĢł
    1.16
    Û
    1.08
    ãĢ
    1.06
    âĸ
    1.06
    âľ
    1.04
    âģ
    1.02
    ï¸
    1.01
    âĶ
    1.00
    Activations Density 1.084%

    No Known Activations