Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 21288
    Prev
    Next
    INDEX
    Explanations

    mentions of sequels

    oai_token-act-pair · gpt-3.5-turbo

    references to sequels in entertainment media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¬¼
    -0.72
    Ľ
    -0.70
    ·
    -0.65
    toggle
    -0.62
    inen
    -0.61
    uda
    -0.60
    Ĭ±
    -0.59
    ãģį
    -0.58
    nutrition
    -0.58
     heterogeneity
    -0.58
    POSITIVE LOGITS
     trilogy
    1.10
     sequel
    0.93
     thereto
    0.92
     sequels
    0.91
     installments
    0.82
    arios
    0.80
     Trilogy
    0.78
     installment
    0.78
    ogue
    0.77
    ngth
    0.76
    Activations Density 0.046%

    No Known Activations