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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17644
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics and politicians

    oai_token-act-pair · gpt-3.5-turbo

    descriptors and attributes used to characterize political figures

    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
     Mayhem
    -0.80
    NetMessage
    -0.78
    ulia
    -0.73
    ipment
    -0.71
    rimination
    -0.70
    ovember
    -0.70
    ulla
    -0.69
    pmwiki
    -0.68
     GEAR
    -0.68
     Panic
    -0.67
    POSITIVE LOGITS
     centrist
    1.37
     principled
    1.32
     pragmatic
    1.27
     prag
    1.23
     progressive
    1.19
     moderate
    1.16
     compassionate
    1.15
     populist
    1.14
    moderate
    1.13
     visionary
    1.11
    Activations Density 0.287%

    No Known Activations