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. 0-RES-JB
    6. 17635
    Prev
    Next
    INDEX
    Explanations

    mentions related to animated content

    oai_token-act-pair · gpt-3.5-turbo

    references to animation and animated works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Church
    -0.73
    chens
    -0.72
     Benz
    -0.72
    Graham
    -0.70
     Graham
    -0.69
    apeake
    -0.69
    Priv
    -0.69
     Patriot
    -0.68
    RELATED
    -0.67
    isd
    -0.66
    POSITIVE LOGITS
     animation
    3.74
     animations
    2.88
     Animation
    2.81
    Animation
    2.52
     anim
    2.03
     animated
    1.98
     animate
    1.88
    anim
    1.86
     Animated
    1.80
     Anim
    1.80
    Activations Density 0.013%

    No Known Activations