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. 6314
    Prev
    Next
    INDEX
    Explanations

    words related to metals, specifically copper

    oai_token-act-pair · gpt-3.5-turbo

    references to copper

    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
    arro
    -0.74
    imaru
    -0.72
    fare
    -0.72
    ROR
    -0.71
    stract
    -0.67
    inen
    -0.67
     Wanted
    -0.66
     Aid
    -0.66
    models
    -0.65
     Nurs
    -0.65
    POSITIVE LOGITS
     oxide
    0.90
     wool
    0.88
     flakes
    0.84
     copper
    0.84
     piping
    0.83
     wire
    0.83
     sulf
    0.81
     ore
    0.81
    plate
    0.79
     pipe
    0.78
    Activations Density 0.014%

    No Known Activations