© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 1545
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "documentary"

    oai_token-act-pair · gpt-3.5-turbo

    references to documentaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffff
    -0.93
    hr
    -0.74
    ingers
    -0.73
    hare
    -0.71
    cream
    -0.69
    adding
    -0.68
    Commerce
    -0.67
    usable
    -0.65
    pace
    -0.64
    uckles
    -0.64
    POSITIVE LOGITS
     documentary
    1.09
     filmmaker
    1.04
     filmmaking
    0.96
     documentaries
    0.90
     film
    0.89
     filmmakers
    0.86
    thouse
    0.80
    arily
    0.80
    document
    0.79
     films
    0.76
    Activations Density 0.016%

    No Known Activations