© 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. 3-RES-JB
    11. 12903
    Prev
    Next
    INDEX
    Explanations

    references to various types of viruses

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific virus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rian
    -0.75
    ĻĤ
    -0.74
    ilts
    -0.73
    notations
    -0.73
    ¥µ
    -0.72
    secut
    -0.72
    ezvous
    -0.72
    ¥ŀ
    -0.70
    otaur
    -0.69
    ŃĶ
    -0.69
    POSITIVE LOGITS
    irus
    1.11
     virus
    1.09
     infection
    0.98
     Virus
    0.98
     infections
    0.96
     viruses
    0.92
     disease
    0.90
     outbreak
    0.88
     infect
    0.85
     outbreaks
    0.83
    Activations Density 0.008%

    No Known Activations