Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2193
    Prev
    Next
    INDEX
    Explanations

    locations/countries

    oai_token-act-pair · gpt-3.5-turbo

    references to countries and regions

    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
     lik
    -0.57
     behavi
    -0.54
     distingu
    -0.52
     streng
    -0.49
     reconc
    -0.49
    itness
    -0.48
     attribute
    -0.47
     tee
    -0.47
     answ
    -0.47
     curve
    -0.45
    POSITIVE LOGITS
    ,
    0.84
     and
    0.76
     etc
    0.74
    thia
    0.73
    ibia
    0.73
     Philippines
    0.70
     Territory
    0.69
     Arabia
    0.68
     Netherlands
    0.67
    ania
    0.67
    Activations Density 0.103%

    No Known Activations