© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 9533
    Prev
    Next
    INDEX
    Explanations

    terms related to the impact of anthropogenic activities on the environment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concepts of carcinogenicity and its scientific implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yard
    -0.72
    rows
    -0.71
    hon
    -0.69
    stood
    -0.67
    aldi
    -0.67
    bourg
    -0.66
    fighter
    -0.66
    ful
    -0.66
    mare
    -0.66
    anooga
    -0.65
    POSITIVE LOGITS
    ogenic
    1.11
     Flavoring
    0.89
    ogens
    0.82
    lihood
    0.77
    otine
    0.76
    osis
    0.72
    iaries
    0.71
    raft
    0.71
    ãĥ¼ãĥĨ
    0.67
    amation
    0.66
    Activations Density 0.017%

    No Known Activations