© 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. 1-RES-JB
    11. 14190
    Prev
    Next
    INDEX
    Explanations

    words related to state-run entities or institutions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "run" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     receptive
    -0.70
    è£ħ
    -0.68
     mature
    -0.66
     Huntington
    -0.64
     favour
    -0.64
    iour
    -0.63
     immature
    -0.63
     notch
    -0.60
     detriment
    -0.60
     feature
    -0.59
    POSITIVE LOGITS
    escape
    1.14
    ners
    1.14
    run
    1.01
    running
    0.93
    swick
    0.89
    boats
    0.87
    boat
    0.83
    nings
    0.83
    quote
    0.80
    runners
    0.79
    Activations Density 0.004%

    No Known Activations