© 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. 12-RES-JB
    11. 3642
    Prev
    Next
    INDEX
    Explanations

    mentions of political ideologies and systems, particularly socialism and democracy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    discussions about political ideologies and their implementation methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    20439
    -0.87
     è£ıè¦ļéĨĴ
    -0.87
    ĸļ
    -0.81
    senal
    -0.81
    wid
    -0.81
    çĶ°
    -0.80
    icum
    -0.79
    ãĤ·
    -0.79
    crop
    -0.77
    Versions
    -0.76
    POSITIVE LOGITS
     compulsion
    1.25
     coercion
    1.22
     persuasion
    1.21
     brute
    1.20
     force
    1.18
     negotiation
    1.08
     fiat
    1.07
     accident
    1.07
     conquest
    1.06
     willpower
    1.05
    Activations Density 0.349%

    No Known Activations