© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12218
    Prev
    Next
    INDEX
    Explanations

    phrases related to political ideologies and revolutionary struggles, particularly focusing on terms related to the proletariat, Leninism, class consciousness, and socialism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to proletarian struggles and socialist ideology

    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
    Pokemon
    -0.95
     pricey
    -0.79
    Alert
    -0.76
    cheat
    -0.76
     HIP
    -0.76
     sushi
    -0.75
    BALL
    -0.73
     prank
    -0.73
    Pokémon
    -0.72
    Buzz
    -0.72
    POSITIVE LOGITS
     anarchism
    1.08
     emanc
    1.02
     anarchist
    1.02
     Marxism
    1.00
     histor
    0.98
     Anarch
    0.98
     intellectuals
    0.97
     Marxist
    0.97
    ivism
    0.96
    ariat
    0.95
    Activations Density 0.481%

    No Known Activations