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. 1-RES-JB
    6. 19817
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people's names, specifically focusing on "Mam" and "Glasziou"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kson
    -0.71
    orld
    -0.69
     diarr
    -0.67
    wrapper
    -0.66
    ¯¯¯¯
    -0.64
    culosis
    -0.62
    eals
    -0.59
    ciating
    -0.59
     personalized
    -0.59
    ighth
    -0.59
    POSITIVE LOGITS
     Mam
    1.18
    umin
    0.91
    amia
    0.90
    uz
    0.85
    lu
    0.80
    ueller
    0.79
    udeau
    0.78
    matical
    0.76
    wit
    0.76
    uj
    0.75
    Activations Density 0.013%

    No Known Activations