© 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. 23019
    Prev
    Next
    INDEX
    Explanations

    technical specifications and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and values related to computer hardware

    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
     Hayward
    -0.83
     Wagner
    -0.82
    aukee
    -0.79
    Hug
    -0.77
    taboola
    -0.77
     Fry
    -0.74
     Hug
    -0.72
     Wag
    -0.72
     Moroc
    -0.70
    chu
    -0.70
    POSITIVE LOGITS
     64
    1.61
     128
    1.52
    64
    1.50
    128
    1.49
     256
    1.48
     4096
    1.48
     32
    1.46
    256
    1.40
    32
    1.37
     2048
    1.36
    Activations Density 0.288%

    No Known Activations