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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 6594
    Prev
    Next
    INDEX
    Explanations

    mentions of antibiotics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to antibiotics and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ership
    -0.79
    yss
    -0.78
    foundland
    -0.72
    edom
    -0.70
    psc
    -0.70
    LESS
    -0.68
    Assembly
    -0.65
    kj
    -0.65
    ITNESS
    -0.65
    ndra
    -0.64
    POSITIVE LOGITS
    illin
    1.03
     antibiotics
    0.99
     antibiotic
    0.96
    icrobial
    0.92
     bacteria
    0.89
    culosis
    0.86
     treatment
    0.85
    iotics
    0.81
     infections
    0.81
     tuberculosis
    0.78
    Activations Density 0.009%

    No Known Activations