© 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. 2-RES-JB
    11. 1708
    Prev
    Next
    INDEX
    Explanations

    phrases related to political ideologies or movements

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with political ideology, particularly those related to Zionism, capitalism, and white supremacy

    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
    ourcing
    -1.03
    bows
    -0.94
    emis
    -0.86
    urat
    -0.85
    ources
    -0.84
    rays
    -0.84
     Drawn
    -0.84
    ional
    -0.82
    avers
    -0.81
    abouts
    -0.81
    POSITIVE LOGITS
     tracts
    0.91
     tendencies
    0.90
     stronghold
    0.87
     enclave
    0.86
     strongh
    0.84
     hegemony
    0.84
     republic
    0.80
     movements
    0.79
     guerrilla
    0.79
     movement
    0.79
    Activations Density 0.047%

    No Known Activations