© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 16396
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences containing the word "Truth"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igan
    -0.72
     sprint
    -0.67
     minor
    -0.67
     pockets
    -0.65
    ipop
    -0.65
     slot
    -0.64
    inarily
    -0.63
    */
    -0.62
     registrations
    -0.62
     interval
    -0.61
    POSITIVE LOGITS
     Truth
    3.88
    Truth
    2.91
    truth
    2.47
     truth
    1.87
     truths
    1.73
     Reality
    1.49
     Honest
    1.28
    Honest
    1.25
     Facts
    1.25
     falsehood
    1.17
    Activations Density 0.012%

    No Known Activations