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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12442
    Prev
    Next
    INDEX
    Explanations

    references to the celebrity Oprah Winfrey

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their actions or statements

    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
     skelet
    -1.02
     tiss
    -0.94
     Palestin
    -0.93
    gewater
    -0.92
    atile
    -0.84
     exha
    -0.82
    usable
    -0.81
     trave
    -0.80
     confir
    -0.78
     reluct
    -0.78
    POSITIVE LOGITS
     Nile
    0.95
    ei
    0.84
     Stephan
    0.71
    rodu
    0.70
    6666
    0.69
     Viktor
    0.67
    Wan
    0.67
    éĢ
    0.65
     Synd
    0.64
    frey
    0.64
    Activations Density 0.035%

    No Known Activations