© 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. 23031
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes

    oai_token-act-pair · gpt-3.5-turbo

    complex concepts related to technology and societal issues

    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
    Ó
    -0.76
    Ñ
    -0.72
    ã
    -0.70
    âĢ
    -0.70
    ãģĨ
    -0.66
    «
    -0.64
     âĢº
    -0.64
    ":["
    -0.64
     Lots
    -0.63
    áµ
    -0.63
    POSITIVE LOGITS
     merely
    0.87
     mere
    0.81
     alas
    0.78
     effortlessly
    0.72
     mirac
    0.71
     painstaking
    0.70
     nowhere
    0.70
     simply
    0.69
     obliter
    0.69
     nonetheless
    0.69
    Activations Density 1.133%

    No Known Activations