© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 21136
    Prev
    Next
    INDEX
    Explanations

    distances or measurements described in some way, often in the context of travel, weight, or relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to spatial measurements involving distance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulate
    -0.85
    ovy
    -0.77
    stal
    -0.76
    itol
    -0.76
    icum
    -0.74
    ulators
    -0.73
    umption
    -0.73
    tle
    -0.73
    lar
    -0.73
    dom
    -0.72
    POSITIVE LOGITS
     travelled
    1.14
     traveled
    1.01
     distance
    0.96
     distances
    0.90
     Distance
    0.82
    finder
    0.80
     separating
    0.78
    AGE
    0.75
    seeing
    0.73
    Distance
    0.71
    Activations Density 0.027%

    No Known Activations