© 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. 1-RES-JB
    11. 3595
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific organizations and their operations

    oai_token-act-pair · gpt-3.5-turbo

    references to intelligence and related agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cthulhu
    -0.80
     Hamburg
    -0.75
     Hiroshima
    -0.74
     Copenhagen
    -0.74
    panic
    -0.74
     Swedish
    -0.72
     Scandinavian
    -0.69
    child
    -0.68
     Frankfurt
    -0.67
     shore
    -0.66
    POSITIVE LOGITS
    IB
    1.29
    ilib
    1.05
    terness
    1.04
    RA
    0.91
    EW
    0.89
    oreal
    0.87
    RI
    0.85
    ARB
    0.85
    BA
    0.84
    ANE
    0.83
    Activations Density 0.005%

    No Known Activations