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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 6196
    Prev
    Next
    INDEX
    Explanations

    proper nouns and phrases that seem related to law or justice

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms related to specific entities or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.92
    ãĥĩãĤ£
    -0.81
    ãĤ¨ãĥ«
    -0.73
    ãĥ¢
    -0.71
    ãĤ®
    -0.68
    ãĥ´ãĤ¡
    -0.67
     phantom
    -0.67
    ãĤ¢ãĥ«
    -0.67
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
    ãĥī
    -0.66
    POSITIVE LOGITS
    anski
    0.72
    bush
    0.68
    uit
    0.68
    arma
    0.66
    ternity
    0.65
    bar
    0.65
    orah
    0.64
    tip
    0.64
    atche
    0.64
    abus
    0.64
    Activations Density 0.063%

    No Known Activations