© 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. 3-RES-JB
    11. 21071
    Prev
    Next
    INDEX
    Explanations

    mentions of locations related to lakes or bodies of water

    oai_token-act-pair · gpt-3.5-turbo

    references to "Lakes"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENTS
    -0.83
    agnar
    -0.77
    ENT
    -0.68
    IBLE
    -0.66
    Reply
    -0.64
    itton
    -0.64
    untu
    -0.63
     cmd
    -0.62
    ENTION
    -0.61
    ested
    -0.60
    POSITIVE LOGITS
    peak
    0.98
    hire
    0.97
     Lakes
    0.97
    creen
    0.86
     Erie
    0.82
    hare
    0.80
     Basin
    0.76
    eries
    0.75
     basin
    0.74
    apeake
    0.73
    Activations Density 0.009%

    No Known Activations