© 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. 4-RES-JB
    11. 22115
    Prev
    Next
    INDEX
    Explanations

    the substring "urinate" with variations in spelling and contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to urination or related activities

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

    No Comments

    Negative Logits
     Dragonbound
    -0.88
    姫
    -0.74
    BOOK
    -0.73
    maker
    -0.72
     Sacrament
    -0.72
    erella
    -0.71
     Dickinson
    -0.69
    makers
    -0.69
     guiActiveUnfocused
    -0.66
    女
    -0.66
    POSITIVE LOGITS
     ur
    1.04
    pee
    1.01
    gencies
    0.94
    pees
    0.93
    pose
    0.86
    inating
    0.80
    ators
    0.79
    anian
    0.78
    ple
    0.76
    andom
    0.76
    Activations Density 0.007%

    No Known Activations