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. 20453
    Prev
    Next
    INDEX
    Explanations

    words related to powder substances

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of powder substances

    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
    ĻĤ
    -0.76
    ocene
    -0.74
    egal
    -0.74
     Democr
    -0.74
    alian
    -0.73
    rian
    -0.69
    nesota
    -0.69
    dfx
    -0.68
    aird
    -0.67
    IAN
    -0.66
    POSITIVE LOGITS
    stals
    0.93
    powder
    0.92
     Powder
    0.90
    flake
    0.87
     powd
    0.85
    roleum
    0.84
     powder
    0.84
    puff
    0.77
    bowl
    0.77
     coating
    0.76
    Activations Density 0.010%

    No Known Activations