© 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. 2-RES-JB
    6. 11477
    Prev
    Next
    INDEX
    Explanations

    terms related to Babylonian culture

    oai_token-act-pair · gpt-3.5-turbo

    references to ancient Babylon and various materials such as cellulose and pulp

    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
    choes
    -0.94
    llan
    -0.86
    htaking
    -0.85
    artney
    -0.84
    lla
    -0.80
    undai
    -0.78
    anmar
    -0.77
    EStream
    -0.75
    aukee
    -0.75
    akening
    -0.74
    POSITIVE LOGITS
    ylon
    0.85
    ISO
    0.83
    itious
    0.82
     ILCS
    0.82
     Empires
    0.77
    ible
    0.74
     pulp
    0.74
    aldehyde
    0.73
     Punjab
    0.72
    seed
    0.69
    Activations Density 0.021%

    No Known Activations