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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 10714
    Prev
    Next
    INDEX
    Explanations

    references to Disney

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Disney and its associated locations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arial
    -0.73
     Centauri
    -0.66
     Adin
    -0.65
    haar
    -0.64
    usterity
    -0.64
     antioxid
    -0.63
    ysis
    -0.62
     fuzz
    -0.61
    idency
    -0.61
    lain
    -0.61
    POSITIVE LOGITS
     XD
    1.01
     Infinity
    0.94
    Sea
    0.93
     Parks
    0.92
    world
    0.90
    Vision
    0.89
     Enterprises
    0.87
    World
    0.86
    plex
    0.85
     Studios
    0.84
    Activations Density 0.027%

    No Known Activations