© 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. 22404
    Prev
    Next
    INDEX
    Explanations

    words related to political ideologies

    oai_token-act-pair · gpt-3.5-turbo

    references to right-wing political affiliations or ideologies

    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
     Remastered
    -0.70
     cellul
    -0.68
    DAQ
    -0.67
    atable
    -0.67
    arette
    -0.67
    è¦ļéĨĴ
    -0.66
    arettes
    -0.65
    ulative
    -0.64
     Mehran
    -0.62
    aples
    -0.61
    POSITIVE LOGITS
    eous
    1.35
     wing
    1.07
    wing
    1.06
     winger
    0.99
     flank
    0.94
     fielder
    0.92
    ward
    0.90
    move
    0.83
     handed
    0.83
    most
    0.78
    Activations Density 0.053%

    No Known Activations