Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18780
    Prev
    Next
    INDEX
    Explanations

    mentions of the brand Chevrolet and related models such as Corvette and Cruze

    oai_token-act-pair · gpt-3.5-turbo

    brand names and models of vehicles, particularly Chevrolet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -1.08
    yss
    -0.88
    ijk
    -0.85
    ĨĴ
    -0.80
    ocrine
    -0.79
    eki
    -0.79
    ĸļ
    -0.78
    umbnail
    -0.78
    angers
    -0.78
    ĺħ
    -0.77
    POSITIVE LOGITS
     Corvette
    1.00
     dealership
    0.92
     Cars
    0.88
     Seat
    0.85
    rolet
    0.85
     Chevrolet
    0.82
     Volt
    0.82
     Chase
    0.82
     Chevy
    0.82
     sedan
    0.77
    Activations Density 0.012%

    No Known Activations