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. 8232
    Prev
    Next
    INDEX
    Explanations

    names or titles related to people in the film industry, such as directors or writers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of directors in a film context

    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
    MpServer
    -0.81
     Leafs
    -0.71
     Labrador
    -0.66
    cup
    -0.65
    affle
    -0.64
    bitcoin
    -0.64
    ulia
    -0.64
    abies
    -0.62
    latable
    -0.62
     Exercise
    -0.61
    POSITIVE LOGITS
    urally
    0.96
     studios
    0.93
     Studios
    0.88
    ial
    0.86
    ography
    0.85
     filmmaker
    0.85
     films
    0.83
     filmmakers
    0.82
    director
    0.82
    cember
    0.81
    Activations Density 0.042%

    No Known Activations