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. 6-RES-JB
    6. 5954
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "gon" which seems to be related to specific treatments or concepts in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the term 'gon' and its variations, indicating a focus on polygon-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.79
    bers
    -0.72
    rosis
    -0.63
    stroke
    -0.62
     reper
    -0.61
    holding
    -0.61
    OTS
    -0.61
    ITED
    -0.59
     sauce
    -0.58
     principled
    -0.57
    POSITIVE LOGITS
    auts
    1.05
    adal
    1.02
    vernment
    0.93
    uclear
    0.92
    xon
    0.91
    nel
    0.91
    spir
    0.90
    ctory
    0.83
    sey
    0.83
    zo
    0.82
    Activations Density 0.067%

    No Known Activations