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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 15401
    Prev
    Next
    INDEX
    Explanations

    words related to swimming

    oai_token-act-pair · gpt-3.5-turbo

    references to swimming activities and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CRIP
    -0.69
    20439
    -0.69
     misplaced
    -0.65
    ________________________
    -0.64
    relevant
    -0.63
    eger
    -0.63
     crushing
    -0.62
     Newsp
    -0.61
     paving
    -0.60
    ribune
    -0.59
    POSITIVE LOGITS
     Swim
    1.28
    suits
    1.10
     swim
    1.09
    suit
    1.09
    boat
    0.93
    boats
    0.90
    estone
    0.89
    borg
    0.87
    tub
    0.87
    wear
    0.84
    Activations Density 0.005%

    No Known Activations