© 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. 11186
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversies or negative events

    oai_token-act-pair · gpt-3.5-turbo

    references to secrets or conspiracies involving influential figures or groups

    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
     retained
    -0.72
     outset
    -0.69
    imentary
    -0.68
     centrally
    -0.68
    eper
    -0.68
     supplemented
    -0.64
    isites
    -0.63
    erial
    -0.63
     strengthened
    -0.62
     memorandum
    -0.62
    POSITIVE LOGITS
    âĢ
    1.29
     Elsa
    1.05
     anime
    1.05
     Naruto
    1.04
     Blizz
    1.04
    âľ
    1.03
    Pokemon
    1.02
     ponies
    1.00
     Twitch
    1.00
    Elsa
    0.99
    Activations Density 0.879%

    No Known Activations