© 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. 10-RES-JB
    6. 10500
    Prev
    Next
    INDEX
    Explanations

    locations or directions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and related spatial or temporal phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascript
    -0.67
     bolstered
    -0.65
    iated
    -0.61
    uable
    -0.59
    umerous
    -0.57
     characterized
    -0.56
     championed
    -0.55
    stories
    -0.55
     propelled
    -0.54
     strategies
    -0.54
    POSITIVE LOGITS
     Calais
    0.87
     Cannes
    0.81
     Hogwarts
    0.80
     Auschwitz
    0.79
     Donetsk
    0.77
     Leeds
    0.75
     Dortmund
    0.73
     Edinburgh
    0.73
     Leicester
    0.72
     Sochi
    0.71
    Activations Density 0.484%

    No Known Activations