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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 440
    Prev
    Next
    INDEX
    Explanations

    references to the car manufacturer "BMW" with varying model numbers and contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the BMW automotive brand

    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
    ional
    -0.89
    arters
    -0.71
    pid
    -0.71
    lement
    -0.69
    aways
    -0.68
    brate
    -0.68
    tainment
    -0.67
    mond
    -0.67
     Lauder
    -0.66
    Las
    -0.66
    POSITIVE LOGITS
    sonian
    0.79
    ueller
    0.79
    OTHER
    0.78
    olitan
    0.75
    oru
    0.74
    imil
    0.72
    BM
    0.71
    OGR
    0.71
    ASS
    0.71
     Mayhem
    0.69
    Activations Density 0.014%

    No Known Activations