© 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. 8-RES-JB
    6. 15025
    Prev
    Next
    INDEX
    Explanations

    words related to spatial or temporal distance

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of distance, particularly in relation to memories or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingen
    -0.96
    lain
    -0.91
    ickson
    -0.89
    udeb
    -0.89
    umen
    -0.84
    leck
    -0.78
    weeney
    -0.76
    ounce
    -0.75
    amacare
    -0.74
    uid
    -0.74
    POSITIVE LOGITS
     relatives
    0.99
     distant
    0.96
     cousin
    0.95
     cousins
    0.91
     shores
    0.85
     neighbours
    0.80
     Territories
    0.79
     neighbour
    0.78
     glances
    0.78
     horizon
    0.76
    Activations Density 0.050%

    No Known Activations