© 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. 4-RES-JB
    6. 2467
    Prev
    Next
    INDEX
    Explanations

    references to Latin America

    oai_token-act-pair · gpt-3.5-turbo

    references to Latin America

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

    No Comments

    Negative Logits
    erker
    -0.85
    hower
    -0.85
    ividual
    -0.83
    jri
    -0.83
    à©
    -0.83
    erk
    -0.82
    ERSON
    -0.79
    */(
    -0.79
    LEASE
    -0.78
    ULL
    -0.78
    POSITIVE LOGITS
    ophone
    0.93
    ophon
    0.85
     pes
    0.81
     Instruments
    0.75
     Latin
    0.74
     Rite
    0.73
     roots
    0.71
    idad
    0.71
     Inquisition
    0.70
    Latin
    0.70
    Activations Density 0.009%

    No Known Activations