© 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. 9-RES-JB
    11. 22975
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences emphasizing strong agreement or support for a particular idea

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "overwhelming" and related phrases indicating a strong consensus or majority opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emis
    -0.81
    rint
    -0.74
    pring
    -0.72
    azine
    -0.72
    hift
    -0.68
    chery
    -0.66
    ringe
    -0.66
    ©¶æ
    -0.65
    hops
    -0.63
    pace
    -0.63
    POSITIVE LOGITS
     majority
    0.93
    whelming
    0.91
     majorities
    0.91
    majority
    0.89
     overwhelming
    0.81
     YES
    0.79
     odds
    0.77
     overwhelmingly
    0.73
     negativity
    0.73
    YES
    0.72
    Activations Density 0.044%

    No Known Activations