© 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
    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. 7833
    Prev
    Next
    INDEX
    Explanations

    phrases related to human rights violations and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to human rights violations and abuses

    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
     calculator
    -0.90
    upiter
    -0.89
     toast
    -0.85
    utherford
    -0.84
    Opt
    -0.84
    mith
    -0.82
     Calculator
    -0.80
    nect
    -0.80
    achus
    -0.80
    fortune
    -0.78
    POSITIVE LOGITS
     impunity
    1.57
     abuses
    1.50
     torture
    1.47
     genocide
    1.45
     atrocities
    1.44
     detainees
    1.43
     Amnesty
    1.42
     violations
    1.38
     persecution
    1.34
     NGOs
    1.34
    Activations Density 0.793%

    No Known Activations