© 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. 18793
    Prev
    Next
    INDEX
    Explanations

    references to downloadable content (DLC) and digital products

    oai_token-act-pair · gpt-3.5-turbo

    elements related to video game content and expansions

    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
    wikipedia
    -0.85
    Ò
    -0.82
     horizont
    -0.78
    Hamilton
    -0.74
    zsche
    -0.73
     Schmidt
    -0.70
     calmly
    -0.70
    NPR
    -0.69
     bicycl
    -0.68
    Wikipedia
    -0.67
    POSITIVE LOGITS
     DLC
    1.69
     expansions
    1.29
     bundle
    1.28
     unlocks
    1.26
     bundles
    1.23
     Xbox
    1.22
    Xbox
    1.22
     Packs
    1.22
     downloadable
    1.22
     multiplayer
    1.21
    Activations Density 0.412%

    No Known Activations