© 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. 665
    Prev
    Next
    INDEX
    Explanations

    references to the word "elephant" and related terms like "ivory" and "seals"

    oai_token-act-pair · gpt-3.5-turbo

    references to elephants and related topics

    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
    pring
    -0.86
    lly
    -0.85
    nder
    -0.84
    nergy
    -0.82
    ndra
    -0.80
    lished
    -0.80
    nces
    -0.80
    nda
    -0.78
    nerg
    -0.76
    mble
    -0.74
    POSITIVE LOGITS
     elephant
    1.32
     elephants
    1.29
    iasis
    1.15
     Elephant
    1.05
     herds
    0.97
     calf
    0.91
     ivory
    0.88
     penis
    0.88
     Haram
    0.86
    ota
    0.86
    Activations Density 0.015%

    No Known Activations