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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 1460
    Prev
    Next
    INDEX
    Explanations

    terms related to the brand "Audi"

    oai_token-act-pair · gpt-3.5-turbo

    references to the brand Audi

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aver
    -0.71
     resent
    -0.67
    rising
    -0.65
    UTC
    -0.64
    ashing
    -0.63
     serving
    -0.63
    =\"
    -0.63
     dest
    -0.62
    ranch
    -0.62
    kin
    -0.61
    POSITIVE LOGITS
     Audi
    4.09
     audi
    1.94
    audi
    1.92
    Aud
    1.89
     Aud
    1.59
     BMW
    1.43
     Volkswagen
    1.42
     Porsche
    1.32
     VW
    1.32
     Audio
    1.32
    Activations Density 0.014%

    No Known Activations