© 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. 7-RES-JB
    11. 23725
    Prev
    Next
    INDEX
    Explanations

    references related to coal, including coal mines, coal cleaning process, coal industry workers, and coal-fired power plants

    oai_token-act-pair · gpt-3.5-turbo

    mentions of coal and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.74
    ij士
    -0.74
    ysis
    -0.73
    ournal
    -0.73
    olon
    -0.72
    ammad
    -0.71
    ROR
    -0.71
    iotics
    -0.70
     Niet
    -0.69
     Vec
    -0.69
    POSITIVE LOGITS
    itions
    1.17
    itional
    1.01
    mining
    1.01
     miner
    1.00
     miners
    1.00
     mining
    0.97
     seams
    0.96
    mine
    0.96
     seam
    0.93
    ition
    0.90
    Activations Density 0.023%

    No Known Activations