© 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. 11-RES-JB
    11. 18529
    Prev
    Next
    INDEX
    Explanations

    political affiliations and beliefs

    oai_token-act-pair · gpt-3.5-turbo

    personal political beliefs and identity assertions

    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
     salv
    -0.73
     enthusi
    -0.72
     brisk
    -0.67
     culminating
    -0.67
     mammoth
    -0.67
     scrimmage
    -0.64
     conclud
    -0.64
     contag
    -0.63
     accelerated
    -0.63
    ¥ŀ
    -0.62
    POSITIVE LOGITS
     I
    1.50
    I
    1.39
     My
    1.21
    My
    1.14
     myself
    1.03
     Honestly
    1.01
     my
    1.01
    my
    0.95
     But
    0.92
     Period
    0.92
    Activations Density 0.416%

    No Known Activations