© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 22515
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Latin" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Latin" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artifacts
    -0.75
    ickr
    -0.70
    washer
    -0.67
    ipeg
    -0.66
    APS
    -0.65
     coaster
    -0.64
    cdn
    -0.64
     override
    -0.63
     clicked
    -0.63
    emaker
    -0.61
    POSITIVE LOGITS
     Latin
    3.86
    Latin
    3.15
     Latino
    1.65
     Latinos
    1.55
     Dominican
    1.55
     Spanish
    1.55
     Hispanic
    1.49
     Mexican
    1.45
     Colombian
    1.43
     Venezuelan
    1.42
    Activations Density 0.016%

    No Known Activations