© 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. 3-RES-JB
    6. 23260
    Prev
    Next
    INDEX
    Explanations

    locations, especially focusing on the city of New York

    oai_token-act-pair · gpt-3.5-turbo

    mentions of locations, particularly New York

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Constantin
    -0.75
     Sear
    -0.71
    ãĤ¦
    -0.67
     Geo
    -0.64
    bearing
    -0.61
     Russ
    -0.61
    compan
    -0.61
     Homo
    -0.58
     Nost
    -0.57
    anthrop
    -0.57
    POSITIVE LOGITS
     CITY
    1.03
     YORK
    0.99
    INESS
    0.95
     TIM
    0.93
    nesday
    0.88
    MAN
    0.84
    ANE
    0.83
     ARTICLE
    0.83
    FORE
    0.81
    aukee
    0.81
    Activations Density 0.011%

    No Known Activations