© 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 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. 0-RES-JB
    11. 13757
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fewer"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fewer."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lly
    -0.65
    front
    -0.60
    host
    -0.60
    nat
    -0.59
    uv
    -0.57
     backdrop
    -0.56
    ende
    -0.56
    ´
    -0.55
    ll
    -0.55
    au
    -0.55
    POSITIVE LOGITS
     fewer
    3.49
     less
    1.74
    few
    1.58
     narrower
    1.35
     shorter
    1.30
     smaller
    1.22
    Few
    1.19
     stricter
    1.19
     Few
    1.15
     tighter
    1.15
    Activations Density 0.012%

    No Known Activations