© 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 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. 9-RES-JB
    11. 14745
    Prev
    Next
    INDEX
    Explanations

    phrases related to human rights organizations and policies

    oai_token-act-pair · gpt-3.5-turbo

    organizations and entities related to human rights advocacy

    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
    achel
    -0.71
    isable
    -0.65
    oling
    -0.65
     seasoning
    -0.64
     exerc
    -0.64
    selection
    -0.64
     curfew
    -0.64
    robe
    -0.64
     arsen
    -0.63
    grade
    -0.61
    POSITIVE LOGITS
     advocacy
    0.93
    Fight
    0.90
     advocates
    0.85
     Advoc
    0.85
     applauded
    0.83
     Equality
    0.82
     advocating
    0.81
     applaud
    0.80
     opposes
    0.80
     activists
    0.79
    Activations Density 0.221%

    No Known Activations