© 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. 10-RES-JB
    11. 10062
    Prev
    Next
    INDEX
    Explanations

    negative connotations or criticism related to right-wing ideology

    oai_token-act-pair · gpt-3.5-turbo

    references to right-wing political ideologies and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     KH
    -0.65
     Prol
    -0.63
     Pell
    -0.62
     Sz
    -0.62
     Solitaire
    -0.61
     Contest
    -0.61
     dism
    -0.59
     Rudd
    -0.59
     Cree
    -0.59
     Siem
    -0.59
    POSITIVE LOGITS
    wing
    1.38
    hander
    1.35
    handed
    1.34
    thinking
    1.29
    leaning
    1.27
    angled
    1.26
    hand
    1.17
    sided
    1.14
    aligned
    1.14
    click
    1.11
    Activations Density 0.031%

    No Known Activations