© 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. 0-RES-JB
    11. 13407
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to the action of washing

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of washing or cleaning

    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
     Goblin
    -0.80
    IG
    -0.72
    FS
    -0.70
    abilities
    -0.70
    UG
    -0.69
    tg
    -0.69
    Tra
    -0.68
    EF
    -0.66
    ingo
    -0.64
    actic
    -0.63
    POSITIVE LOGITS
     washing
    3.48
     washed
    2.96
     wash
    2.47
    washing
    2.45
    washed
    2.13
    wash
    2.11
     bathing
    1.62
     Wash
    1.62
     rinse
    1.55
    washer
    1.53
    Activations Density 0.026%

    No Known Activations