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. 2-RES-JB
    6. 2330
    Prev
    Next
    INDEX
    Explanations

    references to cast and crew members in the context of movies or TV shows

    oai_token-act-pair · gpt-3.5-turbo

    references to a film's cast and production quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Not in Any Lists

    No Comments

    Negative Logits
     administr
    -0.68
     subsistence
    -0.62
     preventive
    -0.61
     Welfare
    -0.59
     unregulated
    -0.59
    osate
    -0.58
     welfare
    -0.57
     coerc
    -0.57
     legisl
    -0.56
     ineffective
    -0.56
    POSITIVE LOGITS
     soundtrack
    0.71
     Ghostbusters
    0.70
     cinematic
    0.70
     sequels
    0.69
     Dracula
    0.68
     comics
    0.67
     anthology
    0.67
     movies
    0.67
    Disney
    0.66
     actress
    0.65
    Activations Density 3.629%

    No Known Activations