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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 20055
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and political issues, such as tax avoidance, voter disenfranchisement, patent infringement, campaign finance violations, democracy-threatening voter suppression, cultural appropriation, gender bias, corporate misconduct, environmental issues, and religious propaganda

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal and political controversies

    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
    ources
    -0.75
     Selected
    -0.69
    »Ĵ
    -0.68
     Tablet
    -0.68
     Compass
    -0.68
    Picture
    -0.66
    aceae
    -0.65
    imentary
    -0.64
    izons
    -0.63
     Ways
    -0.62
    POSITIVE LOGITS
     corruption
    1.31
     abuses
    1.30
     incompetence
    1.30
     sabotage
    1.30
     malf
    1.30
     vandalism
    1.27
     fraud
    1.25
     greed
    1.23
     intimidation
    1.22
     abuse
    1.22
    Activations Density 0.425%

    No Known Activations