© 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. 10-RES-JB
    11. 3097
    Prev
    Next
    INDEX
    Explanations

    words related to global initiatives and financial matters

    oai_token-act-pair · gpt-3.5-turbo

    references to charitable actions and support systems

    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
    paio
    -1.11
     McCabe
    -0.88
     Pats
    -0.87
    Scot
    -0.86
     McA
    -0.84
    bernatorial
    -0.84
     Everett
    -0.84
     Sheriff
    -0.83
    Raid
    -0.82
     Junction
    -0.82
    POSITIVE LOGITS
     countries
    1.81
     nations
    1.66
     OECD
    1.61
     Countries
    1.60
     global
    1.54
     UNESCO
    1.51
     democracies
    1.50
     governments
    1.49
     globalization
    1.46
     globally
    1.43
    Activations Density 0.699%

    No Known Activations