© 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. 10-RES-JB
    11. 9428
    Prev
    Next
    INDEX
    Explanations

    political party names and related words

    oai_token-act-pair · gpt-3.5-turbo

    political party names and affiliations

    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
     Twain
    -0.87
     Yellowstone
    -0.82
    ĸļ
    -0.79
     Bezos
    -0.72
     Ples
    -0.71
    erous
    -0.70
    angelo
    -0.68
     Compton
    -0.67
     McGee
    -0.67
     Sears
    -0.67
    POSITIVE LOGITS
     leader
    1.34
     MLA
    1.26
    Leader
    1.26
     Leader
    1.23
     candidate
    1.19
     Party
    1.18
     manifesto
    1.18
     councillor
    1.17
     legislator
    1.13
     politician
    1.13
    Activations Density 0.178%

    No Known Activations