© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 1748
    Prev
    Next
    INDEX
    Explanations

    words related to alternate worlds or universes

    oai_token-act-pair · gpt-3.5-turbo

    frequent mentions of the term "worlds" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ged
    -0.79
    thumbnails
    -0.76
    ging
    -0.73
    sie
    -0.71
    Downloadha
    -0.70
    ãĥ´ãĤ¡
    -0.70
    ================================================================
    -0.69
    iple
    -0.67
    uez
    -0.67
    é¾įå
    -0.67
    POSITIVE LOGITS
     worlds
    0.94
    hops
    0.90
    peak
    0.88
     collide
    0.86
    chool
    0.85
     Reborn
    0.80
    pace
    0.76
    hell
    0.75
     wide
    0.74
    terness
    0.73
    Activations Density 0.019%

    No Known Activations