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. 9-RES-JB
    6. 3863
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Austin"

    oai_token-act-pair · gpt-3.5-turbo
    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
    */(
    -0.92
    theless
    -0.75
    cribed
    -0.74
    agogue
    -0.73
    cription
    -0.73
     externalToEVAOnly
    -0.72
    iatric
    -0.72
    criptions
    -0.72
    icz
    -0.71
    ppelin
    -0.70
    POSITIVE LOGITS
     Austin
    0.90
     Dillon
    0.83
    Austin
    0.80
     Chronicle
    0.78
     Powers
    0.77
     Petersen
    0.74
    sterdam
    0.74
    ienne
    0.73
     TX
    0.72
    Lee
    0.68
    Activations Density 0.041%

    No Known Activations