© 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. 7-RES-JB
    11. 12411
    Prev
    Next
    INDEX
    Explanations

    references to reality TV shows

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Survivor" reality TV franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anical
    -0.81
    ibrary
    -0.81
    ppo
    -0.80
    iris
    -0.76
    ern
    -0.71
    heric
    -0.71
    mented
    -0.71
    anwhile
    -0.70
    erva
    -0.70
    asio
    -0.70
    POSITIVE LOGITS
     contestants
    1.26
     contestant
    1.18
     Contest
    1.00
     Idol
    0.97
     pageant
    0.94
     idols
    0.87
     Casting
    0.85
     Survivor
    0.83
     Swim
    0.81
     Celebrity
    0.79
    Activations Density 0.057%

    No Known Activations