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. 22771
    Prev
    Next
    INDEX
    Explanations

    specific models of Tesla electric vehicles

    oai_token-act-pair · gpt-3.5-turbo

    references to various electric vehicle models

    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
    nces
    -0.95
    vernment
    -0.83
    di
    -0.75
    ulhu
    -0.73
    bent
    -0.70
    airo
    -0.70
    racial
    -0.69
    omon
    -0.68
    SPONSORED
    -0.67
    olulu
    -0.66
    POSITIVE LOGITS
     Mayhem
    1.01
     Model
    0.77
     Tesla
    0.74
     lineup
    0.72
     âī¡
    0.72
     Reloaded
    0.71
     BMW
    0.69
     maker
    0.69
    Maker
    0.66
     1886
    0.66
    Activations Density 0.017%

    No Known Activations