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. 327
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental ecosystems

    oai_token-act-pair · gpt-3.5-turbo

    references to ecosystems in various contexts

    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
    amiya
    -0.86
    ilts
    -0.74
    rib
    -0.74
    Han
    -0.73
    mad
    -0.72
    zai
    -0.72
    blers
    -0.71
    nell
    -0.71
    aciously
    -0.71
    ners
    -0.70
    POSITIVE LOGITS
     ecosystem
    1.13
     ecosystems
    1.02
     ecology
    0.84
     footprint
    0.79
     flora
    0.74
     evolves
    0.73
     node
    0.73
     integ
    0.72
     synergy
    0.72
    eers
    0.71
    Activations Density 0.015%

    No Known Activations