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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 8508
    Prev
    Next
    INDEX
    Explanations

    phrase related to subscriptions or offerings from The New York Times

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "New York"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cca
    -0.66
    ovember
    -0.64
    ono
    -0.63
    iage
    -0.62
    REL
    -0.61
    WAYS
    -0.60
     mir
    -0.60
    anza
    -0.59
    minist
    -0.59
    itta
    -0.59
    POSITIVE LOGITS
     York
    1.30
     Yorker
    1.05
     YORK
    0.96
     Orleans
    0.92
     Yorkers
    0.89
    York
    0.88
     Zealand
    0.84
     Hampshire
    0.79
    bies
    0.78
     Jersey
    0.78
    Activations Density 0.017%

    No Known Activations