© 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. 4-RES-JB
    11. 15644
    Prev
    Next
    INDEX
    Explanations

    instances where the word "much" is used

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "much."

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

    No Comments

    Negative Logits
    İĭ
    -0.79
    swick
    -0.79
    atures
    -0.77
    esome
    -0.77
    idon
    -0.77
    emy
    -0.76
    agate
    -0.75
    ysc
    -0.72
    ATURES
    -0.68
    ogens
    -0.68
    POSITIVE LOGITS
     ado
    0.85
     appreciated
    0.82
    NESS
    0.78
     esteemed
    0.74
     simpler
    0.73
     MUCH
    0.71
     else
    0.69
     nicer
    0.64
     more
    0.64
    heartedly
    0.63
    Activations Density 0.054%

    No Known Activations