© 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. 7277
    Prev
    Next
    INDEX
    Explanations

    mentions of confidence in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    expressions of confidence or lack thereof in various institutions and entities

    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
    ãĥ¼ãĥ³
    -0.78
    zens
    -0.77
    netflix
    -0.75
    kel
    -0.74
    alde
    -0.72
    idal
    -0.71
    udeb
    -0.70
    ozo
    -0.67
     Tags
    -0.66
    ãĥķãĤ©
    -0.66
    POSITIVE LOGITS
    worthiness
    1.16
     sincerity
    1.09
     reliability
    1.08
     accuracy
    0.99
     integrity
    0.96
     outcome
    0.95
     legitimacy
    0.94
     validity
    0.91
     independence
    0.91
     competence
    0.91
    Activations Density 0.256%

    No Known Activations