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. 10-RES-JB
    6. 4020
    Prev
    Next
    INDEX
    Explanations

    words related to ambition or ambition-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to ambient music and its related aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    creen
    -0.81
    ãĥīãĥ©ãĤ´ãĥ³
    -0.69
     Gutenberg
    -0.67
     learners
    -0.64
     Ragnarok
    -0.63
     Soda
    -0.60
     Mercury
    -0.59
    é¾įå¥ij士
    -0.59
    fork
    -0.59
     Ti
    -0.58
    POSITIVE LOGITS
    assad
    1.35
    iguous
    1.30
    iance
    1.29
    assadors
    1.26
    ience
    1.22
    ivalent
    1.21
    assador
    1.20
    ushed
    1.18
    ushes
    1.15
    ushing
    1.14
    Activations Density 0.023%

    No Known Activations