© 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. 2-RES-JB
    11. 3859
    Prev
    Next
    INDEX
    Explanations

    mentions of conservatives

    oai_token-act-pair · gpt-3.5-turbo

    references to conservatives and discussions involving their views and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fleet
    -0.73
    amaz
    -0.73
    upon
    -0.71
    WAY
    -0.69
    Coach
    -0.68
    ãĤ¨ãĥ«
    -0.68
     Yak
    -0.65
    BY
    -0.64
    chest
    -0.64
     Marathon
    -0.64
    POSITIVE LOGITS
    ervative
    1.12
    ervatives
    1.10
    atism
    0.94
     conservatives
    0.87
     radicals
    0.84
     orthodoxy
    0.80
     thinkers
    0.79
     Protestants
    0.76
     buffs
    0.76
     popul
    0.74
    Activations Density 0.010%

    No Known Activations