© 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 EvalsExportsinterp-engineNEWAPI 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. 20391
    Prev
    Next
    INDEX
    Explanations

    locations or distances related to proximity

    oai_token-act-pair · gpt-3.5-turbo

    references to physical distance and proximity between objects or individuals

    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
    icer
    -0.68
    Form
    -0.68
    orically
    -0.67
    Auth
    -0.66
    Bir
    -0.66
    ulet
    -0.66
    oly
    -0.64
    onut
    -0.63
     ANN
    -0.62
    aml
    -0.62
    POSITIVE LOGITS
     vicinity
    1.05
     proximity
    1.02
     entrances
    0.94
     unprotected
    0.90
     adjacent
    0.89
     nearby
    0.83
     perimeter
    0.83
     desks
    0.82
     vantage
    0.81
     closest
    0.80
    Activations Density 0.334%

    No Known Activations