© 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. 10316
    Prev
    Next
    INDEX
    Explanations

    mentions of the football/soccer team "Dinamo"

    oai_token-act-pair · gpt-3.5-turbo

    references to the team "Dinamo" and its various contexts

    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
    sburgh
    -0.76
    âĢ¢âĢ¢
    -0.71
     Simulator
    -0.65
    inately
    -0.64
    e
    -0.63
     Murd
    -0.62
    BILITIES
    -0.61
    é¾įå¥ij士
    -0.60
    BILITY
    -0.60
    åŃIJ
    -0.57
    POSITIVE LOGITS
    osaurs
    1.35
    ocide
    1.13
    ny
    1.04
    amic
    1.02
    amar
    0.98
    ucle
    0.98
    ners
    0.96
    jury
    0.92
    amo
    0.91
    omial
    0.90
    Activations Density 0.055%

    No Known Activations