© 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. 9-RES-JB
    11. 453
    Prev
    Next
    INDEX
    Explanations

    information related to political polls and the standings of political figures in different regions

    oai_token-act-pair · gpt-3.5-turbo

    references to polling data or statistics 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 @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     licence
    -0.94
    humane
    -0.83
     licences
    -0.82
     civilisation
    -0.81
     apologise
    -0.77
     enqu
    -0.77
     recognise
    -0.76
     infring
    -0.75
     realise
    -0.74
     Honour
    -0.74
    POSITIVE LOGITS
     RNC
    1.33
     POLITICO
    1.31
     Politico
    1.31
     GOP
    1.20
     Rove
    1.18
     polls
    1.17
    Democrats
    1.17
    Republicans
    1.16
     Priebus
    1.16
     polling
    1.15
    Activations Density 1.573%

    No Known Activations