© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 1333
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to meteorology and related fields

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various scientific fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.85
    ortium
    -0.76
    lua
    -0.74
    GREEN
    -0.68
    rained
    -0.67
    rising
    -0.67
    TPP
    -0.67
    nered
    -0.66
    draft
    -0.65
    athing
    -0.65
    POSITIVE LOGITS
    ities
    0.94
    ity
    0.87
     significance
    0.86
     warfare
    0.83
     Warfare
    0.81
    ogical
    0.81
     superiority
    0.78
     correlates
    0.77
    ological
    0.76
     accur
    0.75
    Activations Density 0.035%

    No Known Activations