© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 4366
    Prev
    Next
    INDEX
    Explanations

    information related to political parties, elections, and candidates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to political candidates and their standings in elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irtual
    -0.79
    english
    -0.79
    aimon
    -0.76
    ctica
    -0.71
    region
    -0.70
    ital
    -0.66
    uala
    -0.65
    ĸļ
    -0.63
    amy
    -0.63
    aunders
    -0.61
    POSITIVE LOGITS
     nominee
    1.31
     nominees
    1.25
     contenders
    1.16
     candidate
    1.14
     candidates
    1.13
     contender
    1.10
     frontrunner
    1.04
     spoiler
    1.03
     presumptive
    1.03
     ticket
    1.03
    Activations Density 0.269%

    No Known Activations