© 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. 12104
    Prev
    Next
    INDEX
    Explanations

    mentions of horses in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to horses

    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
    ruct
    -0.78
    imilation
    -0.71
     Compton
    -0.70
    ongyang
    -0.69
    ensing
    -0.67
    ociate
    -0.67
    itu
    -0.67
    idential
    -0.67
     Architects
    -0.66
    ociation
    -0.66
    POSITIVE LOGITS
     horse
    3.70
     horses
    3.22
     Horse
    2.76
    horse
    2.75
     Horses
    2.56
     donkey
    1.77
     camel
    1.74
    orses
    1.57
     cavalry
    1.55
     cow
    1.48
    Activations Density 0.021%

    No Known Activations