© 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. 8-RES-JB
    11. 10218
    Prev
    Next
    INDEX
    Explanations

    concepts related to Marxism and Leninism

    oai_token-act-pair · gpt-3.5-turbo

    academic concepts and theories related to Marxism and its interpretations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gallery
    -0.74
    Lago
    -0.73
    imgur
    -0.72
     coughing
    -0.71
    bucks
    -0.71
    btn
    -0.70
     VIP
    -0.68
     Fiesta
    -0.68
     Veteran
    -0.68
     PHOTO
    -0.67
    POSITIVE LOGITS
    icist
    1.39
     epist
    1.32
     philosophers
    1.30
     theories
    1.29
     Theory
    1.27
     theology
    1.27
     theory
    1.26
     philosophy
    1.19
     dogma
    1.15
     posit
    1.15
    Activations Density 0.649%

    No Known Activations