© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12434
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the word "Ceiling" (often abbreviated as "Ce") in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "Ce" and its variations, indicating a focus on references to the term "Ceasar" or similar contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    rition
    -1.00
    wagen
    -0.99
    bucks
    -0.97
    */(
    -0.94
     Cosponsors
    -0.84
    stadt
    -0.83
    pocket
    -0.83
    marked
    -0.80
    sburg
    -0.77
    rawdownloadcloneembedreportprint
    -0.77
    POSITIVE LOGITS
    asar
    0.91
    asing
    0.89
    asers
    0.87
    plin
    0.86
    ce
    0.84
     Ce
    0.84
    ylon
    0.82
    pt
    0.82
    cca
    0.80
    asion
    0.79
    Activations Density 0.010%

    No Known Activations