© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 10257
    Prev
    Next
    INDEX
    Explanations

    mentions of human rights-related organizations and terms

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights organizations and related activities

    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
     chirop
    -0.73
     inherit
    -0.70
    Kings
    -0.69
    PLA
    -0.68
     Lovecraft
    -0.68
     casinos
    -0.68
     Toast
    -0.67
     Tea
    -0.66
     hairc
    -0.66
     Keynes
    -0.65
    POSITIVE LOGITS
     UNHCR
    1.39
    nesty
    1.25
     NGO
    1.21
     humanitarian
    1.16
     Geneva
    1.14
     Amnesty
    1.12
     NGOs
    1.03
    Syria
    1.03
     Observatory
    0.97
     Refugee
    0.95
    Activations Density 0.367%

    No Known Activations