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. 2934
    Prev
    Next
    INDEX
    Explanations

    words related to waste or unwanted items

    oai_token-act-pair · gpt-3.5-turbo

    words or terms related to waste and recycling

    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
     Byrd
    -0.64
     pronounced
    -0.64
     diplom
    -0.63
     endowed
    -0.62
     princ
    -0.62
     Xavier
    -0.61
     encount
    -0.61
    BILITY
    -0.61
     accomp
    -0.61
    \'
    -0.60
    POSITIVE LOGITS
     Products
    0.86
    grass
    0.86
    Stream
    0.82
    ulent
    0.81
    olit
    0.80
     Seeds
    0.80
     Foods
    0.80
    haus
    0.79
    glass
    0.77
    heimer
    0.76
    Activations Density 0.305%

    No Known Activations