© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11163
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism and attacks towards individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    aggressive language or terms associated with criticism and attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pection
    -0.76
    hazard
    -0.72
    cano
    -0.72
    duct
    -0.70
    poral
    -0.70
    lycer
    -0.70
    yip
    -0.69
    earchers
    -0.69
    trap
    -0.69
    kj
    -0.69
    POSITIVE LOGITS
     critics
    1.01
     liberals
    0.93
     feminists
    0.93
     commenters
    0.91
     fellow
    0.90
     Republicans
    0.90
     politicians
    0.89
     Islam
    0.88
     environmentalists
    0.88
     gays
    0.87
    Activations Density 0.220%

    No Known Activations