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. 4-RES-JB
    6. 5297
    Prev
    Next
    INDEX
    Explanations

    mentions of the brand "Chevrolet"

    oai_token-act-pair · gpt-3.5-turbo

    references to Chevrolet and its vehicle models

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

    No Comments

    Negative Logits
    vironment
    -0.99
    ĺħ
    -0.86
    ijk
    -0.84
    eki
    -0.80
    ĨĴ
    -0.80
    yss
    -0.79
    uality
    -0.76
    urai
    -0.76
    dress
    -0.75
    inen
    -0.74
    POSITIVE LOGITS
     Corvette
    0.99
     dealership
    0.91
     Chevy
    0.90
     Seat
    0.89
     Chase
    0.86
     Cars
    0.86
     Chevrolet
    0.85
     Volt
    0.85
     sedan
    0.79
    rolet
    0.77
    Activations Density 0.011%

    No Known Activations