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. 5681
    Prev
    Next
    INDEX
    Explanations

    references to the word "Lamborghini"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Lam" and its variations, indicating a focus on that entity or subject

    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
    ãģį
    -0.71
     Occupations
    -0.69
    GROUND
    -0.69
     Subtle
    -0.67
    REDACTED
    -0.63
    ģĸ
    -0.62
    ãĥĥãĥĪ
    -0.61
     gradient
    -0.58
    HEAD
    -0.57
    ABLE
    -0.57
    POSITIVE LOGITS
    borgh
    1.44
    inated
    1.04
    ont
    1.03
    oufl
    1.03
    ouse
    1.02
    pling
    0.99
    bs
    0.98
    onte
    0.97
    oran
    0.96
    inate
    0.95
    Activations Density 0.034%

    No Known Activations