© 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. 2-RES-JB
    11. 17585
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Hollywood"

    oai_token-act-pair · gpt-3.5-turbo

    references to Hollywood and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arity
    -0.83
    ktop
    -0.74
    eeper
    -0.69
    aired
    -0.68
    unin
    -0.68
    ebook
    -0.68
    pron
    -0.66
    imov
    -0.66
    gger
    -0.65
    theless
    -0.65
    POSITIVE LOGITS
     Hollywood
    0.99
     studios
    0.96
     Hills
    0.92
    Film
    0.87
     Reporter
    0.86
     Boulevard
    0.86
     Studios
    0.82
     Pictures
    0.80
     studio
    0.78
     mog
    0.77
    Activations Density 0.011%

    No Known Activations