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. 4-RES-JB
    6. 5326
    Prev
    Next
    INDEX
    Explanations

    mentions of film or video production activities

    oai_token-act-pair · gpt-3.5-turbo

    references to film or movie production activities

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

    No Comments

    Negative Logits
    imb
    -0.92
    uckle
    -0.74
    imo
    -0.69
    combe
    -0.69
    leans
    -0.67
    hatt
    -0.63
     whisk
    -0.62
     Seas
    -0.62
    ucket
    -0.60
    ench
    -0.59
    POSITIVE LOGITS
    wright
    0.90
     productions
    0.88
    Production
    0.79
    unit
    0.77
     screenings
    0.72
     studio
    0.71
     studios
    0.71
    smanship
    0.70
    Hunt
    0.69
     production
    0.69
    Activations Density 0.034%

    No Known Activations