© 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. 2701
    Prev
    Next
    INDEX
    Explanations

    terms related to legislation, legal agreements, and legal actions

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

    phrases and terms related to political agreements, laws, and actions

    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
    etheless
    -0.75
     ILCS
    -0.72
    detail
    -0.72
    Ô
    -0.63
    cffff
    -0.62
    hap
    -0.62
    ignty
    -0.61
    eking
    -0.61
    ãģı
    -0.61
    morrow
    -0.61
    POSITIVE LOGITS
     debuted
    1.10
     came
    1.08
     premiered
    1.06
     broke
    1.06
     arrived
    1.05
     went
    1.05
     erupted
    1.04
     began
    1.04
     rolled
    1.03
     became
    1.02
    Activations Density 0.239%

    No Known Activations