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

    Neuronpedia

    Jacobian LensNEW
    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. 3514
    Prev
    Next
    INDEX
    Explanations

    mentions of movies or films

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "film" or "movies."

    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
    -0.89
    BY
    -0.72
    nyder
    -0.71
    bley
    -0.69
     tooth
    -0.66
    ĵĺ
    -0.66
    ppard
    -0.65
     medically
    -0.65
    regulated
    -0.65
    dL
    -0.65
    POSITIVE LOGITS
     films
    0.93
    film
    0.91
     film
    0.91
     adaptation
    0.89
    ography
    0.89
     theaters
    0.86
    Film
    0.85
     screenings
    0.84
     studios
    0.84
    goers
    0.82
    Activations Density 0.037%

    No Known Activations