© 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. 4-RES-JB
    11. 7192
    Prev
    Next
    INDEX
    Explanations

    references to political parties and their actions

    oai_token-act-pair · gpt-3.5-turbo

    references to political party affiliations and their control in government

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

    No Comments

    Negative Logits
    sea
    -0.74
    DragonMagazine
    -0.67
    ouf
    -0.66
    obyl
    -0.66
     disturbance
    -0.66
    atari
    -0.65
    artifacts
    -0.63
    spr
    -0.63
    tnc
    -0.63
     decomp
    -0.63
    POSITIVE LOGITS
    Republicans
    0.90
     nominate
    0.88
    Democrats
    0.86
     caucus
    0.84
     appoint
    0.84
     Santorum
    0.83
     elected
    0.81
     Caucus
    0.80
     factions
    0.79
    isans
    0.79
    Activations Density 0.446%

    No Known Activations