© 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. 4-RES-JB
    11. 1903
    Prev
    Next
    INDEX
    Explanations

    specific mentions of locations or terms related to locating in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geographic locations and their identification

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

    No Comments

    Negative Logits
    kus
    -0.90
    tails
    -0.89
    jin
    -0.88
    ivari
    -0.87
    qs
    -0.87
    haw
    -0.87
    endiary
    -0.82
    icum
    -0.81
    arb
    -0.80
    jug
    -0.80
    POSITIVE LOGITS
     location
    0.82
     scanner
    0.76
     Sensor
    0.76
     locations
    0.75
     landmarks
    0.75
     locate
    0.72
     JPEG
    0.72
     Rover
    0.70
     Location
    0.70
    finder
    0.69
    Activations Density 0.043%

    No Known Activations