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. 8-RES-JB
    6. 8741
    Prev
    Next
    INDEX
    Explanations

    phrases related to maximizing or optimizing something

    oai_token-act-pair · gpt-3.5-turbo

    the concept of maximizing outcomes or efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mare
    -0.81
    mens
    -0.72
    masters
    -0.71
    gar
    -0.70
    riad
    -0.69
    mans
    -0.68
     Vish
    -0.68
    yer
    -0.67
    erie
    -0.66
    eries
    -0.65
    POSITIVE LOGITS
     dstg
    0.73
     capitalize
    0.67
     reproduce
    0.63
    iary
    0.62
     achievable
    0.61
    uder
    0.60
     shortest
    0.60
    ãĥīãĥ©ãĤ´ãĥ³
    0.59
    angles
    0.59
     collabor
    0.58
    Activations Density 0.032%

    No Known Activations