© 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. 9-RES-JB
    11. 1843
    Prev
    Next
    INDEX
    Explanations

    numerical figures and descriptions of oil and trade quantities

    oai_token-act-pair · gpt-3.5-turbo

    data and statistics related to crude oil imports and exports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sych
    -0.91
     Dumbledore
    -0.82
     Investigator
    -0.79
     Resurrection
    -0.77
    misc
    -0.76
    cellence
    -0.75
     OCD
    -0.74
     paranormal
    -0.74
     Personality
    -0.74
    thood
    -0.74
    POSITIVE LOGITS
     exports
    1.72
     export
    1.60
     imports
    1.48
     exporting
    1.45
     OPEC
    1.41
     tariffs
    1.36
     suppliers
    1.36
    export
    1.33
     shipments
    1.30
     commodities
    1.29
    Activations Density 1.155%

    No Known Activations