© 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. 2-RES-JB
    11. 20798
    Prev
    Next
    INDEX
    Explanations

    phrases related to human rights organizations, such as "Human Rights Watch."

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights organizations and related reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cobb
    -0.82
    esville
    -0.78
     Gillespie
    -0.76
     Veh
    -0.75
     Cary
    -0.74
     Coulter
    -0.71
    Denver
    -0.70
    Moore
    -0.69
     Wally
    -0.68
    Town
    -0.68
    POSITIVE LOGITS
     UNHCR
    1.05
     NGO
    0.92
     Refugee
    0.91
     UNESCO
    0.91
     Genocide
    0.87
     Amnesty
    0.85
     NGOs
    0.83
     humanitarian
    0.82
     Framework
    0.81
     delegation
    0.79
    Activations Density 0.170%

    No Known Activations