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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1-RES-JB
    11. 9563
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to feelings of uncertainty or lack of confidence

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "confident" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kinnikuman
    -0.75
    ä½ľ
    -0.73
    ©¶æ¥µ
    -0.72
    minecraft
    -0.71
    senal
    -0.71
    ©¶æ
    -0.69
    ENA
    -0.67
    GET
    -0.67
    Reviewer
    -0.66
    ¾
    -0.66
    POSITIVE LOGITS
    licted
    1.28
    licts
    1.28
    lict
    1.25
    irmation
    1.16
    irms
    1.03
    erences
    1.02
    conf
    1.00
    liction
    1.00
    irming
    0.99
    inement
    0.98
    Activations Density 0.005%

    No Known Activations