Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 19298
    Prev
    Next
    INDEX
    Explanations

    people's names, particularly those with a specific pattern or ending of "uddin"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific names, particularly "uddin" and "Elijah."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mie
    -0.74
    tz
    -0.67
    WORK
    -0.66
    hovah
    -0.64
    eries
    -0.63
    avers
    -0.62
    RAM
    -0.60
    flies
    -0.60
    Ĥİ
    -0.59
    pter
    -0.57
    POSITIVE LOGITS
    uddin
    1.03
    querque
    0.81
    hammad
    0.81
    ãĤ¦ãĤ¹
    0.80
    iosity
    0.78
    ibaba
    0.78
    loo
    0.77
     è£ıè¦ļéĨĴ
    0.73
    herent
    0.73
    iously
    0.72
    Activations Density 0.016%

    No Known Activations