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. 9-RES-JB
    6. 141
    Prev
    Next
    INDEX
    Explanations

    mentions of production studios and their works, particularly focusing on animated motion pictures

    oai_token-act-pair · gpt-3.5-turbo

    references to influential films and filmmakers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebin
    -0.74
     additionally
    -0.65
    imaru
    -0.64
    yne
    -0.63
     consultations
    -0.62
    respond
    -0.62
    sites
    -0.61
     allocated
    -0.60
     complying
    -0.60
     instructed
    -0.60
    POSITIVE LOGITS
     greatness
    1.11
     fame
    1.09
     glory
    0.97
     empires
    0.97
     careers
    0.96
     dynasty
    0.96
     fortunes
    0.90
     legendary
    0.90
     legend
    0.89
     revolution
    0.87
    Activations Density 0.926%

    No Known Activations