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. 5-RES-JB
    6. 13700
    Prev
    Next
    INDEX
    Explanations

    terms related to plant and animal species, ecology, and ecosystem interactions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ecosystems and biodiversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iaz
    -0.78
     machine
    -0.74
    Kick
    -0.71
     Duff
    -0.70
    Machine
    -0.68
     Hogan
    -0.66
    avier
    -0.65
    ZI
    -0.65
    ¶æ
    -0.65
    Dash
    -0.64
    POSITIVE LOGITS
     species
    1.19
     habitats
    1.12
     flora
    1.10
     habitat
    1.10
     biodiversity
    1.09
     biologist
    1.07
     algae
    1.06
    icides
    1.04
     ecology
    1.04
     vegetation
    1.01
    Activations Density 0.125%

    No Known Activations