© 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. 10-RES-JB
    11. 3393
    Prev
    Next
    INDEX
    Explanations

    specific locations related to transportation or organization like stations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or stations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marketable
    -0.72
     nerv
    -0.70
    aphael
    -0.67
    assic
    -0.67
    ":"/
    -0.62
    icit
    -0.62
    erenn
    -0.61
    interstitial
    -0.60
    URES
    -0.60
    stract
    -0.59
    POSITIVE LOGITS
     wagon
    1.14
    ery
    1.13
    wagon
    0.94
     station
    0.91
     stations
    0.87
    yrinth
    0.84
     attendant
    0.82
     Station
    0.79
    arity
    0.79
    mates
    0.78
    Activations Density 0.024%

    No Known Activations