© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4812
    Prev
    Next
    INDEX
    Explanations

    references to academic institutions, universities, colleges, and specific departments within educational organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to prestigious or notable institutions

    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
     fever
    -0.70
    bledon
    -0.67
    wagen
    -0.65
     worry
    -0.62
     strut
    -0.62
     shame
    -0.60
     hunger
    -0.60
     heav
    -0.60
     superv
    -0.60
     jour
    -0.59
    POSITIVE LOGITS
     Philippines
    0.96
     Arts
    0.94
     Ancients
    0.91
     Causes
    0.85
     Republic
    0.85
     Isles
    0.83
     Americas
    0.83
     Atmosp
    0.82
     Environment
    0.81
     Judiciary
    0.80
    Activations Density 0.079%

    No Known Activations