© 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
    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. 20467
    Prev
    Next
    INDEX
    Explanations

    organizations, groups, and institutions with a focus on advocacy, conservation, or non-profit work

    oai_token-act-pair · gpt-3.5-turbo

    references to nonprofit organizations and advocacy groups

    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
    efficients
    -0.92
     Scenes
    -0.89
     Malf
    -0.75
     Joker
    -0.73
    ukong
    -0.72
     Guests
    -0.72
     Countries
    -0.70
     Runes
    -0.69
    iddles
    -0.69
     Strongh
    -0.69
    POSITIVE LOGITS
     nonprofit
    1.43
     organization
    1.42
     advocacy
    1.38
     organisation
    1.21
     group
    1.19
     watchdog
    1.16
     NGO
    1.12
     affiliate
    1.12
     consultancy
    1.10
     association
    1.09
    Activations Density 0.183%

    No Known Activations