© 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. 682
    Prev
    Next
    INDEX
    Explanations

    words related to the word "magma"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of magma

    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
    OPLE
    -0.76
    ãģ¯
    -0.74
    00200000
    -0.74
    Keefe
    -0.73
     Hurricanes
    -0.73
     Goods
    -0.71
    ãĤª
    -0.70
     Toll
    -0.70
     kHz
    -0.70
    ãģį
    -0.70
    POSITIVE LOGITS
    istrates
    1.39
    icka
    1.24
    netic
    1.22
    ikarp
    1.18
    istrate
    1.08
    azine
    1.05
    enta
    0.99
    matically
    0.98
    pie
    0.95
    icians
    0.93
    Activations Density 0.011%

    No Known Activations