Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 4375
    Prev
    Next
    INDEX
    Explanations

    terms related to bacteria

    oai_token-act-pair · gpt-3.5-turbo

    references to bacteria and microbiological concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dash
    -0.74
    park
    -0.73
    pec
    -0.71
     Purs
    -0.68
    aim
    -0.68
    hift
    -0.68
    xxx
    -0.67
    Sum
    -0.66
    Fair
    -0.66
    tower
    -0.65
    POSITIVE LOGITS
     bacteria
    3.42
     bacterial
    2.60
     microbes
    2.51
     bacter
    2.49
    acteria
    2.32
     microbial
    2.22
     coli
    2.08
     microbi
    2.07
     pathogens
    1.90
     microbiota
    1.90
    Activations Density 0.030%

    No Known Activations