© 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. 3175
    Prev
    Next
    INDEX
    Explanations

    terms related to technology advancements and changes in trends

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

    recurring phrases suggesting changes or shifts in circumstances

    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
     corpus
    -0.57
     tert
    -0.50
     helic
    -0.50
     tooltip
    -0.48
     coord
    -0.48
     periodic
    -0.48
    cpp
    -0.48
    trigger
    -0.47
     convol
    -0.47
    earchers
    -0.47
    POSITIVE LOGITS
     either
    1.14
     anymore
    1.02
     nor
    0.94
    nor
    0.86
    èª
    0.84
    Ëľ
    0.74
     anytime
    0.73
    ovie
    0.73
    yet
    0.68
     ¯
    0.65
    Activations Density 0.382%

    No Known Activations