© 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. 22105
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles followed by nouns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "of" in various contexts

    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
    iest
    -0.74
    wcs
    -0.67
    Ô
    -0.67
    ucci
    -0.66
    mie
    -0.66
    Enlarge
    -0.66
     Cosponsors
    -0.65
    ittee
    -0.64
    ESA
    -0.64
    Password
    -0.63
    POSITIVE LOGITS
     varying
    0.78
     assorted
    0.76
     differing
    0.72
     disparate
    0.66
     both
    0.64
     kindred
    0.62
     ours
    0.62
     sorts
    0.62
    emouth
    0.61
    tnc
    0.60
    Activations Density 0.250%

    No Known Activations