© 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. 8-RES-JB
    11. 1072
    Prev
    Next
    INDEX
    Explanations

    places or entities where living beings reside

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of living or dwelling in a specific location

    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
    selage
    -0.70
    othy
    -0.64
    gery
    -0.63
     Barney
    -0.58
    phies
    -0.58
     Airlines
    -0.58
    ãĥª
    -0.56
    sych
    -0.56
    irmation
    -0.56
     clears
    -0.55
    POSITIVE LOGITS
     abroad
    0.91
     outdoors
    0.91
     alongside
    0.88
     indoors
    0.88
     peacefully
    0.86
     atop
    0.86
     ashore
    0.84
     freely
    0.83
     inside
    0.83
     concurrently
    0.83
    Activations Density 0.201%

    No Known Activations