© 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. 19257
    Prev
    Next
    INDEX
    Explanations

    news-related information about people, such as their actions or events in their lives

    oai_token-act-pair · gpt-3.5-turbo

    incidents involving significant actions or events related to individuals

    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
    ··
    -0.69
     mattered
    -0.69
     Coliseum
    -0.65
    uez
    -0.65
    Newsletter
    -0.65
    breakers
    -0.62
     helicop
    -0.62
     Crus
    -0.62
    _-
    -0.60
    bowl
    -0.60
    POSITIVE LOGITS
    CLUS
    0.79
     crowdfunding
    0.72
    ONDON
    0.67
    ISTER
    0.66
    zens
    0.64
    avering
    0.64
    TAIN
    0.64
     extradition
    0.64
    ritten
    0.61
     honour
    0.61
    Activations Density 0.598%

    No Known Activations