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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 6777
    Prev
    Next
    INDEX
    Explanations

    organizations or entities with the term "Foundation" in their name

    oai_token-act-pair · gpt-3.5-turbo

    references to various foundations

    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
    thin
    -0.70
    iple
    -0.69
    selves
    -0.68
    corn
    -0.68
    catentry
    -0.67
    lass
    -0.66
    dos
    -0.65
    Balt
    -0.64
    lan
    -0.64
    cyl
    -0.63
    POSITIVE LOGITS
     Foundation
    0.95
     foundation
    0.80
    onic
    0.75
     trustees
    0.74
    onica
    0.72
     Fund
    0.71
    aires
    0.70
     Institute
    0.69
     donor
    0.69
    ositories
    0.68
    Activations Density 0.016%

    No Known Activations