© 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. 8-RES-JB
    11. 22271
    Prev
    Next
    INDEX
    Explanations

    specific entities mentioned in news articles or journalistic pieces

    oai_token-act-pair · gpt-3.5-turbo

    references to media, particularly journalism, performances, and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izabeth
    -0.70
     EVs
    -0.69
    ascript
    -0.66
    uture
    -0.66
     defin
    -0.63
     fiat
    -0.63
    urion
    -0.62
    +++
    -0.62
    reditary
    -0.62
    ureau
    -0.61
    POSITIVE LOGITS
     boycott
    0.75
     pornographic
    0.73
     jihad
    0.71
     copyrighted
    0.66
     exhib
    0.65
     nightclub
    0.65
    cigarettes
    0.65
    Club
    0.64
     ridic
    0.64
     boycot
    0.64
    Activations Density 0.780%

    No Known Activations