© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11373
    Prev
    Next
    INDEX
    Explanations

    references to American-related entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "American."

    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
    heed
    -0.83
    razil
    -0.70
    NB
    -0.69
    Prev
    -0.67
    RH
    -0.66
    flush
    -0.65
    */(
    -0.64
    ÃŁ
    -0.64
    orders
    -0.64
    ault
    -0.64
    POSITIVE LOGITS
     Airlines
    1.21
     Idol
    1.12
     Samoa
    1.12
    ICAN
    1.01
     Express
    0.92
     Legion
    0.89
    ized
    0.88
     Dream
    0.87
    icus
    0.84
     Pie
    0.84
    Activations Density 0.069%

    No Known Activations