© 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. 7-RES-JB
    11. 22759
    Prev
    Next
    INDEX
    Explanations

    statistical information related to political races

    oai_token-act-pair · gpt-3.5-turbo

    polling data or statistical trends related to political candidates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Starfleet
    -0.75
    RIP
    -0.72
     seasoning
    -0.71
     Collective
    -0.70
     brim
    -0.68
    attribute
    -0.66
     CLSID
    -0.66
     RIP
    -0.64
     eluc
    -0.63
     redundancy
    -0.62
    POSITIVE LOGITS
     challenger
    0.89
     margin
    0.83
     hers
    0.81
    realDonaldTrump
    0.80
     landsl
    0.78
    til
    0.75
     nationally
    0.74
    election
    0.74
     frontrunner
    0.73
     undecided
    0.72
    Activations Density 0.108%

    No Known Activations