© 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. 1-RES-JB
    6. 7221
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific locations or places, particularly those with the term "Ground" in them

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or place named "Ground."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utic
    -0.70
    inen
    -0.69
    HB
    -0.65
    merce
    -0.65
     Bie
    -0.64
     damned
    -0.63
    opes
    -0.63
    ulton
    -0.62
    utations
    -0.62
    esthetic
    -0.61
    POSITIVE LOGITS
    ground
    1.25
    Ground
    1.16
     Ground
    1.02
    hog
    0.88
    stones
    0.85
    spring
    0.79
    plane
    0.78
     ground
    0.77
    water
    0.76
    ashtra
    0.72
    Activations Density 0.007%

    No Known Activations