© 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. 1-RES-JB
    11. 9579
    Prev
    Next
    INDEX
    Explanations

    references to the Spanish language or Spain

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "Spanish" and related references to Spanish context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oscope
    -0.92
    mble
    -0.88
    aucus
    -0.88
    onies
    -0.83
    olulu
    -0.83
    lessly
    -0.81
    imus
    -0.81
    chens
    -0.80
    allery
    -0.79
    ochond
    -0.76
    POSITIVE LOGITS
     Inquisition
    1.33
     Rican
    0.88
     pes
    0.85
     Rico
    0.83
    Spanish
    0.83
     corrid
    0.81
     Spanish
    0.81
     Nieto
    0.80
     Fork
    0.79
     Spain
    0.78
    Activations Density 0.007%

    No Known Activations