© 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. 22360
    Prev
    Next
    INDEX
    Explanations

    statements related to trust and belief

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to trust and confidence

    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
     Nano
    -0.78
     nano
    -0.78
    assic
    -0.70
    phalt
    -0.70
     sax
    -0.70
    irez
    -0.70
    ihu
    -0.68
     Olson
    -0.68
    ames
    -0.68
    illin
    -0.66
    POSITIVE LOGITS
     trust
    2.04
    trust
    1.82
     trusting
    1.78
    Trust
    1.71
     confidence
    1.67
     faith
    1.64
     Trust
    1.64
     belief
    1.61
     trusts
    1.61
     trusted
    1.58
    Activations Density 0.378%

    No Known Activations