© 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. 2-RES-JB
    11. 10385
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific location or name, potentially with a specific cultural or religious association

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific geographic locations or proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hoover
    -0.81
     indo
    -0.66
     Glock
    -0.66
     Olympia
    -0.64
     Gemini
    -0.63
     Curiosity
    -0.63
    PDATE
    -0.63
     biology
    -0.62
     basketball
    -0.62
     Gravity
    -0.61
    POSITIVE LOGITS
    agh
    1.41
    ttp
    1.12
    avan
    1.11
    allery
    1.04
    ilipp
    1.02
    awa
    0.98
    ertility
    0.98
    igans
    0.98
    awan
    0.97
    anas
    0.94
    Activations Density 0.006%

    No Known Activations