© 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. 2-RES-JB
    11. 22405
    Prev
    Next
    INDEX
    Explanations

    terms related to political ideologies and social issues, particularly those with a critical or opposing stance towards capitalism

    oai_token-act-pair · gpt-3.5-turbo

    themes related to social and economic critique

    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
     freezer
    -0.73
     unloaded
    -0.70
     racks
    -0.70
    rolled
    -0.69
     booked
    -0.67
     ineligible
    -0.67
     roof
    -0.67
    ributes
    -0.66
    anka
    -0.66
     notified
    -0.66
    POSITIVE LOGITS
     Chomsky
    0.85
     moreover
    0.84
    SPONSORED
    0.84
     nihil
    0.83
     Nietzsche
    0.82
     Marxism
    0.82
     Narr
    0.80
     Religion
    0.79
     narratives
    0.78
    ablishment
    0.78
    Activations Density 2.669%

    No Known Activations