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

    Neuronpedia

    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. 11-RES-JB
    11. 23284
    Prev
    Next
    INDEX
    Explanations

    programming languages and related frameworks

    oai_token-act-pair · gpt-3.5-turbo

    mentions of programming languages and their frameworks

    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
    76561
    -0.90
    interstitial
    -0.79
    amount
    -0.75
    cffffcc
    -0.68
    Town
    -0.66
    deals
    -0.64
     Gamble
    -0.64
     halftime
    -0.62
    姫
    -0.62
     Deaths
    -0.62
    POSITIVE LOGITS
     backend
    1.21
     ported
    1.19
     implementations
    1.18
     APIs
    1.16
     SDK
    1.16
     libraries
    1.15
     compiler
    1.09
     runtime
    1.08
     statically
    1.07
     plugins
    1.06
    Activations Density 0.250%

    No Known Activations