© 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. 1-RES-JB
    11. 5577
    Prev
    Next
    INDEX
    Explanations

    references to the entertainment industry, particularly focusing on Hollywood

    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 @ 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
    arity
    -0.90
    ebook
    -0.78
    ktop
    -0.72
    imov
    -0.70
    unin
    -0.69
    gger
    -0.69
    idem
    -0.67
    tf
    -0.64
    onies
    -0.64
    eeper
    -0.64
    POSITIVE LOGITS
     Hollywood
    1.22
     studios
    0.96
     Reporter
    0.92
     Boulevard
    0.92
     Hills
    0.92
    rities
    0.83
     Studios
    0.82
    Film
    0.80
     Cinema
    0.80
    enthal
    0.80
    Activations Density 0.009%

    No Known Activations