© 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. 23735
    Prev
    Next
    INDEX
    Explanations

    words related to the oil industry or chemical substances

    oai_token-act-pair · gpt-3.5-turbo

    negative terms associated with the oil and gas industry

    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
     Chiefs
    -0.75
     execut
    -0.70
     Polk
    -0.69
    @@@@
    -0.68
     Mock
    -0.68
     Vaughn
    -0.67
     Lumpur
    -0.67
     BB
    -0.66
    ulhu
    -0.66
     Moody
    -0.65
    POSITIVE LOGITS
    producing
    1.43
    based
    1.32
    laden
    1.29
    related
    1.28
    bearing
    1.27
    induced
    1.23
    fuel
    1.23
    filled
    1.23
    derived
    1.21
    intensive
    1.21
    Activations Density 0.093%

    No Known Activations