© 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. 11-RES-JB
    11. 21312
    Prev
    Next
    INDEX
    Explanations

    words related to different types of fuels, such as coal, oil, natural gas, and uranium

    oai_token-act-pair · gpt-3.5-turbo

    mentions of fossil fuels and natural resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Headquarters
    -0.77
     Collider
    -0.76
     Approach
    -0.70
     Showdown
    -0.70
     Administ
    -0.69
     Victims
    -0.69
     Universities
    -0.68
     Programs
    -0.68
     Administrator
    -0.68
     Employees
    -0.67
    POSITIVE LOGITS
     copper
    1.15
     wool
    1.11
     limestone
    1.09
     metals
    1.08
     wheat
    1.07
     steel
    1.07
     aluminium
    1.07
     zinc
    1.07
     titanium
    1.07
     plastics
    1.04
    Activations Density 0.178%

    No Known Activations