© 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. 11-RES-JB
    11. 24395
    Prev
    Next
    INDEX
    Explanations

    phrases related to religious scripture being considered authoritative

    oai_token-act-pair · gpt-3.5-turbo

    references to religious texts and their interpretations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ktop
    -0.77
     stunts
    -0.77
    NetMessage
    -0.74
     layoffs
    -0.71
     disruptions
    -0.71
     spikes
    -0.71
    Pool
    -0.71
    cffff
    -0.70
    hov
    -0.69
     queues
    -0.69
    POSITIVE LOGITS
     infall
    1.50
     authoritative
    1.45
     accurate
    1.38
     trustworthy
    1.37
     valid
    1.35
     truthful
    1.34
     correct
    1.32
     true
    1.24
     truth
    1.24
     conclusive
    1.20
    Activations Density 0.382%

    No Known Activations