© 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. 2-RES-JB
    11. 22515
    Prev
    Next
    INDEX
    Explanations

    words related to volcanic activity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to volcanic activity

    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
    vest
    -0.83
    Standard
    -0.81
    abet
    -0.78
    practice
    -0.77
    arel
    -0.75
    anded
    -0.74
    arnaev
    -0.73
    Ohio
    -0.71
    Pract
    -0.70
    winner
    -0.70
    POSITIVE LOGITS
     eru
    1.58
     eruption
    1.45
     volcano
    1.32
     volcan
    1.25
     erupt
    1.15
     volcanic
    1.13
     crater
    1.11
     lava
    1.06
     Volcano
    1.01
     erupted
    0.88
    Activations Density 0.014%

    No Known Activations