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. 2-RES-JB
    6. 3667
    Prev
    Next
    INDEX
    Explanations

    proper nouns or phrases related to individuals or places, potentially with a pattern of "az" followed by a number varying from 9 to 10

    oai_token-act-pair · gpt-3.5-turbo

    the name "Az" or variations of it

    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
     Kraken
    -0.67
     Fargo
    -0.64
    ãĤ©
    -0.64
     foremost
    -0.63
     Towns
    -0.63
     Kepler
    -0.63
     Kardashian
    -0.63
     Seah
    -0.62
     Impossible
    -0.62
     proportional
    -0.59
    POSITIVE LOGITS
    az
    1.10
    ombie
    1.08
    azel
    1.00
    eez
    0.98
    awa
    0.98
    quez
    0.97
    aza
    0.95
    ahar
    0.94
    hou
    0.94
    iah
    0.94
    Activations Density 0.012%

    No Known Activations