© 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. 7593
    Prev
    Next
    INDEX
    Explanations

    information related to upcoming elections

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to upcoming elections and their contexts

    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
    ãģķ
    -0.86
     Cargo
    -0.74
    Crew
    -0.70
    SourceFile
    -0.69
    Charge
    -0.67
    Flying
    -0.66
     disembark
    -0.65
     behav
    -0.63
    âĹ¼
    -0.62
    SOURCE
    -0.61
    POSITIVE LOGITS
     elections
    1.07
     polls
    1.02
    election
    0.91
     ballot
    0.91
    stakes
    0.91
    oters
    0.91
     midterm
    0.91
     ballots
    0.90
     winners
    0.89
     winner
    0.89
    Activations Density 0.325%

    No Known Activations