© 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. 8-RES-JB
    11. 17914
    Prev
    Next
    INDEX
    Explanations

    names of cities

    oai_token-act-pair · gpt-3.5-turbo

    names of cities or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Weaver
    -0.62
    rogens
    -0.60
     Finder
    -0.59
     steroids
    -0.58
    rek
    -0.57
    cientious
    -0.57
     constitu
    -0.56
     Aware
    -0.55
     Surviv
    -0.55
     Inher
    -0.55
    POSITIVE LOGITS
     Lumpur
    0.83
    bourg
    0.78
    furt
    0.76
     Angeles
    0.73
    opolis
    0.72
    mington
    0.70
    city
    0.70
    stown
    0.69
    sterdam
    0.69
    zhou
    0.68
    Activations Density 0.124%

    No Known Activations