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. 3140
    Prev
    Next
    INDEX
    Explanations

    titles of movie sequels

    oai_token-act-pair · gpt-3.5-turbo

    titles of movies, games, or franchises

    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
     ende
    -0.72
     sprinkled
    -0.68
    uyomi
    -0.67
     shenan
    -0.66
     pse
    -0.66
     circum
    -0.65
     needles
    -0.65
     choir
    -0.64
     embro
    -0.63
     haste
    -0.63
    POSITIVE LOGITS
    ihilation
    0.88
    unknown
    0.79
     Interface
    0.73
     Definitive
    0.70
    rossover
    0.70
     Missions
    0.70
     Edition
    0.69
    omaly
    0.68
     Unt
    0.68
    VIDIA
    0.68
    Activations Density 0.129%

    No Known Activations