© 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. 0-RES-JB
    11. 15695
    Prev
    Next
    INDEX
    Explanations

    terms related to advanced medical conditions and treatments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to advocacy and support, particularly for social issues and health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ius
    -0.73
    SON
    -0.73
    arus
    -0.71
    oglobin
    -0.68
    ãĥ¢
    -0.65
    lund
    -0.65
     dams
    -0.64
    ULE
    -0.63
     Zhou
    -0.62
    TON
    -0.62
    POSITIVE LOGITS
    adv
    2.93
    Adv
    2.79
     Adv
    2.63
     Advocate
    2.09
     adv
    1.72
     ATM
    1.62
     ADV
    1.57
     Aj
    1.18
     Advance
    1.11
    adj
    1.10
    Activations Density 0.067%

    No Known Activations