© 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. 2-RES-JB
    11. 17508
    Prev
    Next
    INDEX
    Explanations

    the phrase "no-brainer" or words related to certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to certainty and indisputable statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atile
    -0.95
    comings
    -0.89
    ez
    -0.72
    iqu
    -0.71
    rams
    -0.70
     poles
    -0.70
    airs
    -0.70
    otes
    -0.70
     talents
    -0.69
    ions
    -0.68
    POSITIVE LOGITS
     certainty
    0.74
    hood
    0.73
    brainer
    0.72
    QUIRE
    0.69
    TI
    0.66
    ++++++++++++++++
    0.65
    Deal
    0.64
    HEAD
    0.64
    bind
    0.63
     guiName
    0.63
    Activations Density 0.033%

    No Known Activations