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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 5978
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of multiple, different worlds or realities

    oai_token-act-pair · gpt-3.5-turbo

    references to fictional or conceptual "worlds"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.81
    thumbnails
    -0.80
    ged
    -0.74
    ging
    -0.71
    200000
    -0.67
    00000
    -0.63
    Mob
    -0.63
    ible
    -0.62
    riage
    -0.62
    tk
    -0.62
    POSITIVE LOGITS
     worlds
    1.20
     Worlds
    0.93
     universes
    0.82
    chool
    0.79
     Torment
    0.75
     realms
    0.75
     Reborn
    0.74
     Ceres
    0.73
     Scion
    0.73
     planets
    0.73
    Activations Density 0.014%

    No Known Activations