© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 6180
    Prev
    Next
    INDEX
    Explanations

    patterns related to geological events and climate change

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" and references to geographic or regional contexts

    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
    Uber
    -0.79
    ãĤ£
    -0.74
    APD
    -0.73
    Voice
    -0.71
    anasia
    -0.69
    employ
    -0.68
    racist
    -0.67
    hemy
    -0.64
    Sex
    -0.61
    Judge
    -0.61
    POSITIVE LOGITS
     Antarctica
    1.27
     Siberia
    1.23
     situ
    1.14
     Yellowstone
    1.11
     Greenland
    1.09
     northwestern
    1.07
     captivity
    1.06
     northeastern
    1.06
     mountainous
    1.05
     southwestern
    1.05
    Activations Density 0.210%

    No Known Activations