© 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. 4-RES-JB
    11. 1724
    Prev
    Next
    INDEX
    Explanations

    mentions of locations near bodies of water, specifically the seaside

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "side" and its variations

    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
    enegger
    -1.03
    cci
    -0.89
    thening
    -0.83
    ELS
    -0.82
    STER
    -0.82
    ulf
    -0.81
    URE
    -0.79
    URES
    -0.78
    olds
    -0.76
    uum
    -0.75
    POSITIVE LOGITS
    boarding
    0.73
     Dhabi
    0.66
     thirds
    0.65
    medi
    0.64
     sympath
    0.61
     Nightmares
    0.61
    hare
    0.60
     frustrations
    0.60
     Siren
    0.60
     setbacks
    0.60
    Activations Density 0.014%

    No Known Activations