Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 19463
    Prev
    Next
    INDEX
    Explanations

    phrases related to political extremism

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express violence, fear, and manipulation in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inguished
    -0.68
     appreciated
    -0.68
    gor
    -0.63
    arkable
    -0.63
    Berry
    -0.62
    aird
    -0.61
    igmatic
    -0.61
    orb
    -0.61
    venants
    -0.61
     Finder
    -0.60
    POSITIVE LOGITS
     scapego
    1.08
     baseless
    0.96
     hatred
    0.89
     unnecessarily
    0.88
     pretext
    0.86
     impunity
    0.86
     unchecked
    0.84
     gull
    0.83
     slander
    0.83
     phony
    0.83
    Activations Density 0.648%

    No Known Activations