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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 7891
    Prev
    Next
    INDEX
    Explanations

    references to the entertainment industry

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Hollywood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subs
    -0.74
     carts
    -0.72
    uter
    -0.72
     pt
    -0.72
    nav
    -0.71
    ect
    -0.70
    È
    -0.69
    âĶĢ
    -0.68
    pair
    -0.67
     respons
    -0.67
    POSITIVE LOGITS
     Hollywood
    3.64
    ollywood
    2.24
     filmmaking
    1.55
     Spielberg
    1.51
     filmmakers
    1.47
     MGM
    1.46
     cinematic
    1.45
     Paramount
    1.44
     movie
    1.42
     Beverly
    1.41
    Activations Density 0.016%

    No Known Activations