© 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. 10-RES-JB
    11. 11322
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical settings and landscapes

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of serene natural environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agonist
    -0.91
    APD
    -0.82
    agonists
    -0.81
    handler
    -0.81
    ENTION
    -0.79
    Assistant
    -0.78
     Canaver
    -0.76
    rection
    -0.76
    IGN
    -0.75
    Problem
    -0.74
    POSITIVE LOGITS
     sunset
    1.34
     sunlight
    1.34
     breeze
    1.31
     moss
    1.30
     trees
    1.29
     clouds
    1.28
     shimmer
    1.27
     dusk
    1.27
     rain
    1.26
     valleys
    1.25
    Activations Density 0.394%

    No Known Activations