© 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. 1073
    Prev
    Next
    INDEX
    Explanations

    people's first names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Dan" in various contexts

    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
    eering
    -0.65
    llor
    -0.62
     conspicuous
    -0.60
     susceptibility
    -0.60
     margins
    -0.59
     extremes
    -0.57
     ensuring
    -0.57
    saf
    -0.57
     limiting
    -0.56
     imperson
    -0.56
    POSITIVE LOGITS
    zig
    1.40
    ilo
    1.29
    forth
    1.19
    ube
    0.99
    wei
    0.98
    ica
    0.97
    coni
    0.95
     Rather
    0.94
    bury
    0.92
    vers
    0.90
    Activations Density 0.014%

    No Known Activations