© 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. 4223
    Prev
    Next
    INDEX
    Explanations

    the word "Quite" used in sentences

    oai_token-act-pair · gpt-3.5-turbo
    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
    duct
    -0.72
    kamp
    -0.70
    wark
    -0.69
    dies
    -0.69
    clud
    -0.67
    adium
    -0.67
    igans
    -0.67
    ulator
    -0.66
    Ó
    -0.66
    duction
    -0.65
    POSITIVE LOGITS
    entimes
    1.14
     importantly
    1.09
     unsurprisingly
    1.07
    nown
    1.06
     surprisingly
    1.01
    withstanding
    0.95
    etheless
    0.86
     ironic
    0.83
     interestingly
    0.81
     majorities
    0.80
    Activations Density 0.138%

    No Known Activations