© 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. 24573
    Prev
    Next
    INDEX
    Explanations

    words with the specific character "w" and the digits "9" and "10" in close proximity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'w'

    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
     mosqu
    -0.86
     distingu
    -0.82
    milo
    -0.71
     clen
    -0.71
     hemor
    -0.71
     paraly
    -0.70
     unpre
    -0.70
    staking
    -0.69
    uate
    -0.69
     guarding
    -0.68
    POSITIVE LOGITS
    atts
    1.38
    itness
    1.34
    elcome
    1.33
    ashington
    1.19
    izard
    1.16
    restling
    1.15
    irts
    1.13
    isdom
    1.13
    edge
    1.11
    arranted
    1.11
    Activations Density 0.025%

    No Known Activations