© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 2204
    Prev
    Next
    INDEX
    Explanations

    references to brand names, especially related to automotive industry

    oai_token-act-pair · gpt-3.5-turbo

    references to specific car brands and models, particularly Volkswagen and Audi

    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
    -1.06
    ned
    -1.00
    esty
    -0.85
    xual
    -0.78
    ns
    -0.77
    stery
    -0.75
    llular
    -0.75
    forth
    -0.72
    ny
    -0.71
    mits
    -0.70
    POSITIVE LOGITS
     Polo
    0.85
    geist
    0.73
     merch
    0.68
     Pascal
    0.68
    glass
    0.67
    chio
    0.65
    ogl
    0.65
    obook
    0.64
    CHAT
    0.61
    ively
    0.61
    Activations Density 0.084%

    No Known Activations