© 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. 8-RES-JB
    11. 20235
    Prev
    Next
    INDEX
    Explanations

    mentions of elected officials

    oai_token-act-pair · gpt-3.5-turbo

    references to elected officials and the concept of election itself

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iday
    -0.80
    istics
    -0.80
    oken
    -0.75
    ijk
    -0.75
    othe
    -0.75
    ijn
    -0.74
    stocks
    -0.74
    iger
    -0.70
    zac
    -0.69
    Lens
    -0.68
    POSITIVE LOGITS
     representatives
    0.89
     election
    0.88
     elected
    0.86
     committees
    0.85
    eering
    0.85
     elections
    0.84
     officials
    0.84
     mayor
    0.84
     unanimously
    0.82
     leaders
    0.81
    Activations Density 0.039%

    No Known Activations