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. 4725
    Prev
    Next
    INDEX
    Explanations

    references to the term "Bilderberg" and related entities or topics

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations and groups, particularly "Bild" and "Kraftwerk"

    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
    okemon
    -0.77
    orthy
    -0.77
    itamin
    -0.74
    phis
    -0.70
    ONSORED
    -0.70
     vain
    -0.70
    FTWARE
    -0.69
    ouring
    -0.69
    CE
    -0.67
    activated
    -0.67
    POSITIVE LOGITS
     Bild
    1.15
    sonian
    0.73
    ische
    0.73
    glers
    0.69
    lore
    0.68
    ags
    0.68
    sche
    0.68
    otten
    0.67
    heim
    0.65
    ÃĽ
    0.65
    Activations Density 0.012%

    No Known Activations