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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 23103
    Prev
    Next
    INDEX
    Explanations

    mentions of bacterial-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to bacteria and their role in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ignment
    -0.86
    fman
    -0.84
    onga
    -0.84
    ership
    -0.81
    UTC
    -0.77
    quished
    -0.77
    iscons
    -0.76
     largeDownload
    -0.75
    fax
    -0.74
    nels
    -0.73
    POSITIVE LOGITS
     bacteria
    1.17
     spores
    1.10
     infections
    1.10
     infection
    1.08
     pathogens
    1.02
    bial
    1.02
     strains
    0.96
     flora
    0.94
     bacter
    0.93
     organisms
    0.92
    Activations Density 0.056%

    No Known Activations