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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 7633
    Prev
    Next
    INDEX
    Explanations

    health-related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health services and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.75
    ãĥĦ
    -0.69
    assian
    -0.65
    rane
    -0.64
    theless
    -0.63
    bear
    -0.63
    ä¸Ģ
    -0.62
    é¾įå¥ij士
    -0.62
    rogens
    -0.61
    INTON
    -0.60
    POSITIVE LOGITS
    deen
    0.78
    edIn
    0.70
     Premiership
    0.60
     Revenge
    0.59
    rift
    0.58
    illy
    0.58
    iety
    0.56
    udeb
    0.55
    aughters
    0.55
     Humanity
    0.55
    Activations Density 0.315%

    No Known Activations