© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 1231
    Prev
    Next
    INDEX
    Explanations

    mentions of transportation locations, specifically "stations"

    oai_token-act-pair · gpt-3.5-turbo

    references to various stations, possibly transportation or military strategic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marketable
    -0.78
     nerv
    -0.69
    zanne
    -0.66
    aphael
    -0.61
     pestic
    -0.61
    ulkan
    -0.59
    emort
    -0.59
    ":"/
    -0.58
    zes
    -0.58
    umenthal
    -0.58
    POSITIVE LOGITS
    ery
    1.24
     wagon
    1.18
    wagon
    1.00
    arity
    0.90
     station
    0.84
     stations
    0.80
    yrinth
    0.79
     attendant
    0.78
    pole
    0.76
    inson
    0.76
    Activations Density 0.051%

    No Known Activations