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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 22645
    Prev
    Next
    INDEX
    Explanations

    mentions of a particular fictional character

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Gandalf from the "Lord of the Rings" and "Hobbit" series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Lord of the ring related characters, concepts and places.

    Lord of the ring related characters, concepts and places, but they need to start with a capital letter.

    Words related to Lord of the rings, or that sound like words related to Lord of the Rings.

    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
    •LOTR

    No Comments

    Negative Logits
    âĸ¬
    -0.81
    aminer
    -0.78
    âķIJ
    -0.72
    âķIJâķIJ
    -0.71
    Ŀ
    -0.69
    amples
    -0.68
    hift
    -0.68
    ciples
    -0.68
    packages
    -0.66
    eper
    -0.63
    POSITIVE LOGITS
    olkien
    0.99
     Tolkien
    0.98
     Gand
    0.96
     Hobbit
    0.95
     Bagg
    0.93
    alf
    0.83
     hob
    0.81
    gob
    0.79
    inka
    0.75
     Lann
    0.75
    Activations Density 0.024%

    No Known Activations