© 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. 1-RES-JB
    11. 3774
    Prev
    Next
    INDEX
    Explanations

    filmmakers or related terms within the text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to filmmakers and the filmmaking profession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bath
    -0.86
    iba
    -0.80
    affle
    -0.77
    lynn
    -0.74
    affles
    -0.72
    abo
    -0.69
    uter
    -0.69
    phia
    -0.68
    bos
    -0.67
    omaly
    -0.67
    POSITIVE LOGITS
     filmmakers
    1.37
     filmmaker
    1.36
     filmmaking
    1.27
     Films
    1.11
    Film
    1.10
     films
    1.07
     film
    1.05
     Film
    1.04
     studios
    1.04
    film
    1.01
    Activations Density 0.026%

    No Known Activations