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. 23775
    Prev
    Next
    INDEX
    Explanations

    locations or settings described by surroundings or being surrounded by something, potentially highlighting a sense of enclosure or emphasis on the environment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "surrounded by."

    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
    bach
    -0.73
    afe
    -0.73
    iland
    -0.71
    ndum
    -0.68
    reads
    -0.68
    nea
    -0.67
     reproduce
    -0.67
    eva
    -0.67
    ITH
    -0.67
    geist
    -0.66
    POSITIVE LOGITS
     hordes
    0.79
     mobs
    0.72
    products
    0.70
     dozens
    0.70
     dots
    0.68
     myriad
    0.65
     various
    0.64
     kindred
    0.63
     arrows
    0.62
    66666666
    0.61
    Activations Density 0.067%

    No Known Activations