© 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. 1117
    Prev
    Next
    INDEX
    Explanations

    phrases related to notable individuals or places

    oai_token-act-pair · gpt-3.5-turbo

    names or terms related to specific individuals or entities

    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
     swing
    -0.73
     establishment
    -0.72
     lottery
    -0.69
     litter
    -0.68
    Âł
    -0.68
     multim
    -0.66
     Planned
    -0.65
     nationally
    -0.63
     ACC
    -0.61
     multi
    -0.61
    POSITIVE LOGITS
    eli
    1.15
    kowski
    1.10
    gaard
    1.07
    ansky
    1.06
    ouf
    1.05
    zynski
    1.03
    anski
    1.02
    nikov
    1.02
    kov
    1.02
    chenko
    1.02
    Activations Density 0.294%

    No Known Activations