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. 0-RES-JB
    6. 16009
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific type of vehicle - the Mini

    oai_token-act-pair · gpt-3.5-turbo

    references to specific car models, particularly the Mini and BMW

    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
    gil
    -0.74
    Columb
    -0.73
    dal
    -0.72
     scal
    -0.71
    nels
    -0.71
    writ
    -0.70
    ounty
    -0.69
     Columbus
    -0.68
    ollo
    -0.65
     typh
    -0.64
    POSITIVE LOGITS
     BMW
    1.77
     Mous
    1.68
     Mini
    1.50
     McF
    1.49
    iba
    1.42
     Azerbaijan
    1.27
     Boris
    1.25
     Fischer
    1.21
     Azerbai
    1.15
    Mini
    1.11
    Activations Density 0.054%

    No Known Activations