© 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. 6-RES-JB
    6. 20645
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical landscapes, specifically mentioning hills

    oai_token-act-pair · gpt-3.5-turbo

    references to hills or elevated terrains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uality
    -0.88
    ~~~~
    -0.73
    ually
    -0.70
    URES
    -0.69
     Mock
    -0.68
    uve
    -0.67
     Ens
    -0.65
    iling
    -0.65
    cius
    -0.65
     Rabbit
    -0.64
    POSITIVE LOGITS
    side
    1.07
    tops
    0.98
    arious
    0.95
    iage
    0.88
    otropic
    0.83
    stead
    0.82
    top
    0.81
    axe
    0.80
    frog
    0.79
    bike
    0.78
    Activations Density 0.031%

    No Known Activations