© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 1136
    Prev
    Next
    INDEX
    Explanations

    words related to the activity of swimming

    oai_token-act-pair · gpt-3.5-turbo

    activities related to swimming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dom
    -0.69
    tar
    -0.66
     Prescott
    -0.66
    tm
    -0.65
    tek
    -0.64
    riber
    -0.64
    Guy
    -0.63
     KC
    -0.62
    inder
    -0.61
    uler
    -0.61
    POSITIVE LOGITS
     swimming
    3.74
     swim
    2.64
     bathing
    2.03
     Swim
    1.88
     sailing
    1.74
     skating
    1.59
     drowning
    1.59
     surfing
    1.58
     aquatic
    1.56
     canoe
    1.55
    Activations Density 0.016%

    No Known Activations