© 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. 1-RES-JB
    11. 7154
    Prev
    Next
    INDEX
    Explanations

    terms related to Spanish-speaking regions or culture

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific person or entity related to economics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acles
    -0.86
    raised
    -0.82
    unders
    -0.73
    growth
    -0.71
    race
    -0.68
    orph
    -0.67
    utm
    -0.66
    ulse
    -0.66
    acle
    -0.66
    urst
    -0.65
    POSITIVE LOGITS
    ÃŃa
    1.35
     José
    1.08
    ÃŃn
    0.97
    quez
    0.95
     Gomez
    0.95
     Pablo
    0.93
     Toro
    0.91
     Javier
    0.90
     Rica
    0.89
    ÅĤ
    0.87
    Activations Density 0.005%

    No Known Activations