© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 22572
    Prev
    Next
    INDEX
    Explanations

    keywords related to the technology publication "Ars."

    oai_token-act-pair · gpt-3.5-turbo

    the term "Ars" and its variants, possibly related to a specific organization or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fulness
    -0.75
     Independence
    -0.68
    FUL
    -0.68
    tsky
    -0.67
    fully
    -0.61
     Portsmouth
    -0.59
     Kavanaugh
    -0.58
     Kendrick
    -0.58
    vich
    -0.58
    rers
    -0.58
    POSITIVE LOGITS
    ene
    1.12
    è
    1.04
    wered
    0.98
    Techn
    0.91
    ensibly
    0.91
    ignt
    0.89
    acs
    0.88
    abella
    0.87
    linger
    0.87
    ocrates
    0.86
    Activations Density 0.050%

    No Known Activations