© 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. 23590
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals and locations

    oai_token-act-pair · gpt-3.5-turbo

    themes related to tunneling and surveillance

    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
     Temp
    -0.79
    IME
    -0.75
     tem
    -0.74
    ICLE
    -0.72
     temp
    -0.70
     GOODMAN
    -0.67
     Tem
    -0.65
     trump
    -0.65
     Tanz
    -0.63
     Gim
    -0.62
    POSITIVE LOGITS
    heed
    0.90
    bed
    0.88
    pes
    0.87
    hire
    0.85
    roxy
    0.85
    quartered
    0.85
    ulously
    0.85
    nel
    0.85
    geon
    0.84
    everal
    0.84
    Activations Density 0.025%

    No Known Activations