© 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. 1-RES-JB
    11. 3678
    Prev
    Next
    INDEX
    Explanations

    words related to opposition or criticism against something, particularly social or political groups

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to anti-establishment sentiments or opposition to various ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Halls
    -0.83
     Remastered
    -0.80
    ODY
    -0.75
     Lawn
    -0.74
     Legends
    -0.73
     Serve
    -0.72
     Vaults
    -0.69
    estial
    -0.69
    inders
    -0.69
     Wheels
    -0.68
    POSITIVE LOGITS
     anti
    1.03
    establishment
    1.00
    abortion
    0.94
    anti
    0.92
     antic
    0.87
     sympath
    0.84
    inflammatory
    0.83
    overty
    0.81
    war
    0.79
    jud
    0.78
    Activations Density 0.018%

    No Known Activations