© 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. 20429
    Prev
    Next
    INDEX
    Explanations

    two-digit numbers with an activation value ranging from 8 to 10

    oai_token-act-pair · gpt-3.5-turbo

    numerical rankings and statistics in a sports context

    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
     therap
    -0.89
    entimes
    -0.87
     resort
    -0.85
     polluted
    -0.81
     behavi
    -0.80
     peac
    -0.78
     contrace
    -0.78
     periodic
    -0.77
     intensive
    -0.76
     consume
    -0.76
    POSITIVE LOGITS
     Kyle
    1.39
     Dustin
    1.37
     Julio
    1.36
     Jonathan
    1.36
     Josh
    1.36
     Aaron
    1.35
     Jake
    1.34
     Corey
    1.34
     Kevin
    1.33
     Zach
    1.32
    Activations Density 0.205%

    No Known Activations