© 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. 1-RES-JB
    11. 9543
    Prev
    Next
    INDEX
    Explanations

    mentions of activities related to swimming

    oai_token-act-pair · gpt-3.5-turbo

    references to swimming and bathing activities

    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
    eq
    -0.72
     Engel
    -0.67
    bart
    -0.66
    pora
    -0.65
    relevant
    -0.65
     Midlands
    -0.65
     erroneous
    -0.65
    oppers
    -0.63
    ________________________
    -0.62
    avez
    -0.62
    POSITIVE LOGITS
     swimming
    1.21
     swim
    1.06
     Swim
    1.04
     pools
    0.92
    boat
    0.91
    estone
    0.90
    tub
    0.88
    boats
    0.86
    pool
    0.86
     pool
    0.86
    Activations Density 0.010%

    No Known Activations