© 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. 7074
    Prev
    Next
    INDEX
    Explanations

    words related to physical movement or activity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "running."

    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
    ortium
    -0.74
    orescent
    -0.69
    alam
    -0.68
    hran
    -0.68
    oral
    -0.68
    berra
    -0.68
    imei
    -0.67
    olid
    -0.67
    olia
    -0.65
    issan
    -0.65
    POSITIVE LOGITS
    running
    0.90
     running
    0.89
    Running
    0.86
     RUN
    0.80
     Runner
    0.80
     Running
    0.78
     runners
    0.77
     mate
    0.77
     rampant
    0.76
    runners
    0.75
    Activations Density 0.024%

    No Known Activations