© 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. 13808
    Prev
    Next
    INDEX
    Explanations

    organizations or foundations dedicated to specific causes or missions

    oai_token-act-pair · gpt-3.5-turbo

    organizations and initiatives focused on advocacy and support for various rights and social issues

    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
    pload
    -0.90
    Nusra
    -0.83
     Flavoring
    -0.75
    EStream
    -0.75
    Closure
    -0.74
    thora
    -0.72
    éļ
    -0.72
    SpaceEngineers
    -0.71
    Cooldown
    -0.70
    Mrs
    -0.69
    POSITIVE LOGITS
     aspiring
    0.94
     excellence
    0.94
     grassroots
    0.92
     inspirational
    0.88
     unbiased
    0.88
     nonpartisan
    0.87
     educating
    0.87
     empowering
    0.87
     inspiring
    0.86
     innovative
    0.85
    Activations Density 0.415%

    No Known Activations