© 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. 1447
    Prev
    Next
    INDEX
    Explanations

    words related to verifying or disputing facts

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance of factual accuracy and evidence

    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
    married
    -0.75
    cheon
    -0.72
    wic
    -0.71
    inoa
    -0.70
    emaker
    -0.70
    uel
    -0.69
    lav
    -0.69
    Lago
    -0.69
    earable
    -0.69
    aspberry
    -0.68
    POSITIVE LOGITS
     facts
    1.35
     conclusions
    1.24
     factual
    1.24
     truths
    1.23
     conjecture
    1.21
     logic
    1.18
     nuance
    1.13
     hypotheses
    1.13
     falsehood
    1.09
     anecdotes
    1.09
    Activations Density 0.227%

    No Known Activations