© 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. 18608
    Prev
    Next
    INDEX
    Explanations

    political, cultural, and religious affiliations or associations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political or ethnic identities

    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
    Ó
    -0.84
    Ö¼
    -0.74
    Ïī
    -0.72
    sein
    -0.70
    ̶
    -0.69
    Õ
    -0.69
    same
    -0.69
    ||||
    -0.68
    orative
    -0.68
    stretched
    -0.68
    POSITIVE LOGITS
     commentators
    1.26
     historians
    1.24
     observers
    1.23
     scholars
    1.16
     activists
    1.16
     analysts
    1.12
     historian
    1.10
     politicians
    1.10
     journalists
    1.10
     officials
    1.08
    Activations Density 0.300%

    No Known Activations