© 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. 21294
    Prev
    Next
    INDEX
    Explanations

    references to geological features, specifically related to sea level rise and geological faults

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geological features and phenomena, particularly focusing on faults and sea level changes

    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
    advertising
    -0.75
    ZI
    -0.74
     Tradable
    -0.73
    RON
    -0.72
    CHO
    -0.71
    URA
    -0.70
    --------------------------------------------------------
    -0.69
    DEF
    -0.69
    OTO
    -0.69
     Wong
    -0.69
    POSITIVE LOGITS
     basin
    1.01
     lake
    0.92
     Basin
    0.91
     lakes
    0.90
     habitats
    0.89
     ridge
    0.86
     cliffs
    0.85
     habitat
    0.85
     dams
    0.84
     migr
    0.83
    Activations Density 0.212%

    No Known Activations