© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 13280
    Prev
    Next
    INDEX
    Explanations

    criticisms related to politics and economic systems

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to government and corporate interests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    canon
    -0.71
    anguage
    -0.71
    hooting
    -0.69
     Dresden
    -0.66
     Purg
    -0.63
    contact
    -0.63
     Symptoms
    -0.62
    hn
    -0.62
     Norn
    -0.60
    theless
    -0.59
    POSITIVE LOGITS
     billionaires
    1.38
     corporations
    1.33
     wealthy
    1.28
     olig
    1.23
     millionaires
    1.21
     lobbyists
    1.20
     wealthiest
    1.17
     greedy
    1.13
     multinational
    1.12
     billionaire
    1.11
    Activations Density 0.520%

    No Known Activations