© 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. 0-RES-JB
    11. 5414
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Horse" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to "Horse" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     questioning
    -0.69
     sil
    -0.66
    reens
    -0.66
     middle
    -0.64
    theless
    -0.63
     fortune
    -0.63
     mistrust
    -0.63
     cursing
    -0.62
     tut
    -0.62
     semantic
    -0.62
    POSITIVE LOGITS
     Horse
    3.75
     Horses
    1.59
    horse
    1.28
     Elephant
    1.26
     Bunny
    1.13
     Goat
    1.13
     Cobra
    1.11
     Legs
    1.05
     Sheep
    1.03
     Toad
    1.03
    Activations Density 0.029%

    No Known Activations