© 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. 3-RES-JB
    11. 18301
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences containing the word "much"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "much" used to express a lack of quantity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    İĭ
    -0.95
    idon
    -0.90
    atures
    -0.84
    swick
    -0.81
    yg
    -0.79
    ades
    -0.78
    yne
    -0.78
    agate
    -0.77
    etts
    -0.77
    utenberg
    -0.77
    POSITIVE LOGITS
     else
    0.93
     ado
    0.91
     appreciated
    0.78
     avail
    0.78
    NESS
    0.72
     MUCH
    0.71
     longer
    0.70
     hype
    0.68
     fun
    0.67
     luck
    0.66
    Activations Density 0.047%

    No Known Activations