© 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. 2-RES-JB
    11. 17695
    Prev
    Next
    INDEX
    Explanations

    specific references to districts, especially in relation to politics or governance

    oai_token-act-pair · gpt-3.5-turbo

    references to electoral districts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ods
    -0.74
    Accessory
    -0.72
    lihood
    -0.70
    KEY
    -0.69
    ELY
    -0.68
    issan
    -0.67
    FUL
    -0.67
    TAIN
    -0.66
    jamin
    -0.65
    sight
    -0.65
    POSITIVE LOGITS
    ricting
    1.04
    avorite
    0.97
     districts
    0.93
    ynski
    0.76
    rict
    0.75
    hips
    0.74
    lation
    0.73
    rats
    0.71
    ometimes
    0.70
    atown
    0.70
    Activations Density 0.008%

    No Known Activations