© 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. 10493
    Prev
    Next
    INDEX
    Explanations

    phrases related to media critique and government manipulation

    oai_token-act-pair · gpt-3.5-turbo

    references to media manipulation and propaganda

    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
    Berry
    -0.73
    oother
    -0.73
    atta
    -0.72
    cially
    -0.72
    esa
    -0.72
    teness
    -0.72
    fecture
    -0.71
    ameda
    -0.71
    ciplinary
    -0.70
    availability
    -0.70
    POSITIVE LOGITS
     fascist
    1.00
     propaganda
    0.98
     thugs
    0.98
     phony
    0.97
     dictators
    0.96
     Illuminati
    0.95
     hypocrisy
    0.94
     neocons
    0.94
     Capitalism
    0.93
     disinformation
    0.93
    Activations Density 1.311%

    No Known Activations