© 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. 0-RES-JB
    11. 11890
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations, particularly cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    important
    -0.93
     Deploy
    -0.71
     Kab
    -0.61
     overboard
    -0.60
     because
    -0.58
     note
    -0.56
     until
    -0.56
     buff
    -0.55
     improvised
    -0.55
     Eventually
    -0.55
    POSITIVE LOGITS
    arest
    4.37
    arer
    1.17
    apest
    1.08
    hest
    1.03
    atha
    0.92
    orest
    0.90
    cles
    0.88
     deepest
    0.88
    areth
    0.87
    byss
    0.87
    Activations Density 0.004%

    No Known Activations