© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 18007
    Prev
    Next
    INDEX
    Explanations

    GPS coordinates or reservation-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical coordinates and reservation-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iencies
    -0.98
    eared
    -0.88
    earing
    -0.84
    pson
    -0.84
    ogg
    -0.81
    illance
    -0.77
    sle
    -0.75
    ilies
    -0.75
    ilities
    -0.75
    bara
    -0.74
    POSITIVE LOGITS
     Vie
    0.88
    naire
    0.66
    ally
    0.66
    ogue
    0.66
    irie
    0.66
     reservations
    0.65
    ois
    0.64
     Tasman
    0.63
     Sigma
    0.63
     kilometres
    0.62
    Activations Density 0.090%

    No Known Activations