© 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. 17355
    Prev
    Next
    INDEX
    Explanations

    criticisms or discussions related to different aspects of the political left

    oai_token-act-pair · gpt-3.5-turbo

    references to the political left and its characteristics

    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
    alez
    -0.81
     Frey
    -0.73
    actionDate
    -0.71
    oun
    -0.70
     DRAG
    -0.69
    riott
    -0.68
    è¦ļéĨĴ
    -0.67
     Allaah
    -0.67
    Ö¼
    -0.65
    ãĥĺãĥ©
    -0.65
    POSITIVE LOGITS
    wing
    1.14
    overs
    1.04
    ward
    0.97
     wing
    0.94
     orthodoxy
    0.85
     fringe
    0.84
     hemisphere
    0.83
     populism
    0.82
    hander
    0.80
     flank
    0.78
    Activations Density 0.032%

    No Known Activations