© 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. 4-RES-JB
    11. 16526
    Prev
    Next
    INDEX
    Explanations

    mentions of bacteria, particularly in the context of infection and medical treatment

    oai_token-act-pair · gpt-3.5-turbo

    references to bacteria and their roles in various biological contexts

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

    No Comments

    Negative Logits
    UTC
    -0.87
     largeDownload
    -0.85
    quished
    -0.75
    ership
    -0.73
    dash
    -0.73
    umbn
    -0.71
    iscons
    -0.67
    onga
    -0.67
    ibur
    -0.66
    Dash
    -0.66
    POSITIVE LOGITS
     bacteria
    1.21
     flora
    1.05
     infections
    1.03
     spores
    1.02
    bial
    0.99
     infection
    0.98
     microbi
    0.96
     microbes
    0.94
     pathogens
    0.93
     organisms
    0.91
    Activations Density 0.012%

    No Known Activations