© 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. 3-RES-JB
    11. 1784
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific brand or company name

    oai_token-act-pair · gpt-3.5-turbo

    references to the brand or entity associated with the name "Oy" and related words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.79
    FB
    -0.79
    ب
    -0.78
    tumblr
    -0.76
    igion
    -0.76
    IBLE
    -0.75
    Ùħ
    -0.74
    ========
    -0.73
    ievers
    -0.72
    iever
    -0.72
    POSITIVE LOGITS
     oy
    1.17
     Oy
    0.99
    ster
    0.98
    ovy
    0.88
    bean
    0.86
    sters
    0.86
    beans
    0.78
    ridge
    0.77
    nect
    0.77
    shell
    0.76
    Activations Density 0.010%

    No Known Activations