© 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. 11-RES-JB
    11. 7072
    Prev
    Next
    INDEX
    Explanations

    text related to software development and tools

    oai_token-act-pair · gpt-3.5-turbo

    references to video game development tools and modding systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hamilton
    -0.95
     Barron
    -0.80
     graphene
    -0.80
    oglu
    -0.77
     Puerto
    -0.76
    ÄŁ
    -0.76
     Hamilton
    -0.75
     Fuk
    -0.74
     Coul
    -0.73
     Kaufman
    -0.73
    POSITIVE LOGITS
     Skyrim
    2.12
     Bethesda
    1.80
     Fallout
    1.66
     Oblivion
    1.64
     Morrow
    1.62
     mods
    1.61
    yrim
    1.59
    hesda
    1.58
     Mods
    1.43
    Mods
    1.38
    Activations Density 0.281%

    No Known Activations