© 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. 2-RES-JB
    11. 12921
    Prev
    Next
    INDEX
    Explanations

    information related to harmful substances or pathogens in different environments, especially water sources

    oai_token-act-pair · gpt-3.5-turbo

    content related to health and environmental impacts of pathogens and toxins

    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
    ĪĴ
    -0.69
    ãĥ¼ãĥĨãĤ£
    -0.64
    ä¸Ĭ
    -0.64
    ij士
    -0.64
     Honour
    -0.63
    Liberal
    -0.60
    iquette
    -0.60
    ticket
    -0.60
    iversary
    -0.58
     Franch
    -0.58
    POSITIVE LOGITS
     pathogens
    0.90
     dehyd
    0.88
     organisms
    0.88
     bacteria
    0.85
     toxins
    0.85
     biochemical
    0.84
     microbes
    0.84
     genetically
    0.83
     nutrients
    0.83
     genetic
    0.82
    Activations Density 3.011%

    No Known Activations