© 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. 7-RES-JB
    11. 17265
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations, with a focus on cities and areas

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations, particularly places associated with "Lake"

    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
    binary
    -0.80
    schild
    -0.74
    gets
    -0.70
    hered
    -0.69
     streng
    -0.67
    âĶģ
    -0.66
    mble
    -0.64
    GES
    -0.64
    versions
    -0.64
     mitigating
    -0.63
    POSITIVE LOGITS
     City
    1.01
    apolis
    0.88
     Springs
    0.88
     Arabia
    0.86
     Tribune
    0.84
     Lake
    0.79
     Canyon
    0.76
     Rapids
    0.76
     Falls
    0.74
    City
    0.73
    Activations Density 0.018%

    No Known Activations