© 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. 7-RES-JB
    11. 23107
    Prev
    Next
    INDEX
    Explanations

    names or terms starting with "Ce"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Ce" or "Ceiling" in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagen
    -0.94
    bucks
    -0.86
     mileage
    -0.76
    */(
    -0.75
    rition
    -0.71
    pocket
    -0.70
    sburg
    -0.69
    STER
    -0.66
     Cosponsors
    -0.66
    marked
    -0.66
    POSITIVE LOGITS
    ylon
    1.03
    asers
    1.01
    asar
    0.96
    asing
    0.94
    plin
    0.93
    pt
    0.91
    gged
    0.90
    ggie
    0.90
    lements
    0.90
    llan
    0.89
    Activations Density 0.027%

    No Known Activations