© 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. 4-RES-JB
    11. 4202
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations or geographic entities

    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
    ²¾
    -0.69
    TAIN
    -0.69
    cigarettes
    -0.67
    Ķ
    -0.65
    ł
    -0.62
    é¾įå¥ij士
    -0.61
    conserv
    -0.61
    ĵ
    -0.60
     advis
    -0.60
     dispos
    -0.60
    POSITIVE LOGITS
     Museum
    0.80
     Massacre
    0.78
     Herald
    0.78
     Redemption
    0.77
     logo
    0.76
     Folk
    0.74
     Offensive
    0.73
     Effect
    0.72
     Movement
    0.72
     Amendments
    0.71
    Activations Density 0.914%

    No Known Activations