© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 11249
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to politics and government officials

    oai_token-act-pair · gpt-3.5-turbo

    prominent political figures and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Translation
    -0.64
    Els
    -0.60
     Pengu
    -0.57
    ãĥ¼ãĥĨ
    -0.57
    âĶģ
    -0.55
    Redd
    -0.55
    bearing
    -0.54
    ãĥ¬
    -0.53
    farious
    -0.53
    âĸ¬âĸ¬
    -0.51
    POSITIVE LOGITS
     has
    1.19
     insists
    1.14
     wants
    1.12
     undertook
    1.11
     intends
    1.09
     refuses
    1.09
     believes
    1.08
     denies
    1.07
     reacted
    1.07
     expects
    1.07
    Activations Density 0.763%

    No Known Activations