© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 10435
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to Colombia

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or regions

    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
     srfAttach
    -0.75
    jri
    -0.74
    repre
    -0.74
    idays
    -0.72
    thodox
    -0.67
    learn
    -0.67
    retty
    -0.66
     sqor
    -0.66
     overdue
    -0.64
    yip
    -0.61
    POSITIVE LOGITS
    estine
    0.70
     Sonia
    0.68
    neck
    0.67
    adelphia
    0.65
    uration
    0.65
    uses
    0.64
    MX
    0.63
    iers
    0.63
    ordes
    0.63
     Rasm
    0.62
    Activations Density 0.084%

    No Known Activations