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. 5-RES-JB
    6. 14303
    Prev
    Next
    INDEX
    Explanations

    references to the name "Gandolf"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Gandolf."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kick
    -0.74
    alysis
    -0.69
    Kit
    -0.68
     notor
    -0.64
    organic
    -0.62
     porous
    -0.59
    agra
    -0.59
    nexus
    -0.59
     situ
    -0.59
     Achievements
    -0.59
    POSITIVE LOGITS
    dinand
    1.35
    erick
    1.00
    stad
    0.99
    sburg
    0.95
    sson
    0.95
    riction
    0.88
    ocity
    0.88
    enstein
    0.87
    olph
    0.87
    inations
    0.87
    Activations Density 0.021%

    No Known Activations