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. 12-RES-JB
    6. 15249
    Prev
    Next
    INDEX
    Explanations

    references or mentions of media outlets or organizations' names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    proper nouns and specific organizational names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPA
    -0.70
    %%%%
    -0.66
    bys
    -0.65
    uj
    -0.64
    nyder
    -0.62
    bnb
    -0.61
    wat
    -0.60
    cart
    -0.60
    axis
    -0.60
    spons
    -0.59
    POSITIVE LOGITS
     GEAR
    0.73
    ICAN
    0.68
    ¢
    0.65
    azon
    0.65
    Ķ
    0.65
    ITED
    0.65
    oline
    0.61
     Dakota
    0.60
    olated
    0.59
     Down
    0.58
    Activations Density 0.222%

    No Known Activations