© 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. 4126
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases with specific numbers and related delimiters

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

    expressions related to physical sensations or reactions

    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
     constitu
    -0.72
     Solutions
    -0.68
     ado
    -0.68
     credentials
    -0.67
     disposition
    -0.67
     reproduction
    -0.66
     obser
    -0.66
     continuum
    -0.65
     Ceres
    -0.65
     clues
    -0.65
    POSITIVE LOGITS
    deep
    1.32
    jab
    1.19
    dropping
    1.16
    raising
    1.09
    laugh
    1.07
    dry
    1.04
    tw
    1.03
    laun
    1.03
    high
    1.01
    hur
    1.01
    Activations Density 0.094%

    No Known Activations