© 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. 1-RES-JB
    11. 3112
    Prev
    Next
    INDEX
    Explanations

    words related to resistance or protection against something, often in the context of medicine or materials

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "resistant" used in various contexts related to medical resistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPA
    -0.90
    hire
    -0.79
    =-=-=-=-
    -0.76
    apeake
    -0.70
     largeDownload
    -0.70
    ľ
    -0.69
     Blow
    -0.69
     Bohem
    -0.66
    gone
    -0.65
    ĺ
    -0.65
    POSITIVE LOGITS
     resistant
    1.20
     suscept
    1.00
    resistant
    0.97
    adoes
    0.91
     millenn
    0.83
    istant
    0.81
     susceptible
    0.80
     immunity
    0.79
     corrosion
    0.78
     tolerant
    0.78
    Activations Density 0.011%

    No Known Activations