© 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 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. 6-RES-JB
    11. 17889
    Prev
    Next
    INDEX
    Explanations

    terms related to political ideologies and critiques within the left-leaning spectrum

    oai_token-act-pair · gpt-3.5-turbo

    references to political ideologies associated with the left

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alez
    -0.80
     Allaah
    -0.72
    ãĥīãĥ©
    -0.71
    è¦ļéĨĴ
    -0.70
    CLASSIFIED
    -0.70
    Ö¼
    -0.67
     Unloaded
    -0.66
    andise
    -0.65
     Continuous
    -0.65
     Ake
    -0.64
    POSITIVE LOGITS
    wing
    1.17
     wing
    1.10
    overs
    0.94
    ward
    0.91
     orthodoxy
    0.87
     radicals
    0.86
     flank
    0.84
     populism
    0.83
     communists
    0.81
     hemisphere
    0.80
    Activations Density 0.048%

    No Known Activations