© 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. 6-RES-JB
    11. 16878
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions and accusations like "smear," "defamation," "slander," and "libel."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to defamation and slander in media contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udeau
    -0.71
    aldo
    -0.70
     Odyssey
    -0.69
    aldi
    -0.68
    changes
    -0.67
    odes
    -0.67
    negie
    -0.64
    annis
    -0.64
    OTA
    -0.63
    alo
    -0.63
    POSITIVE LOGITS
     smear
    1.00
     slander
    0.96
     libel
    0.85
     accusation
    0.78
     accusations
    0.75
     vil
    0.75
     mole
    0.75
     allegations
    0.75
     leveled
    0.72
     against
    0.71
    Activations Density 0.043%

    No Known Activations