© 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. 2-RES-JB
    11. 21006
    Prev
    Next
    INDEX
    Explanations

    city names

    oai_token-act-pair · gpt-3.5-turbo

    city or town names and their references in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¯
    -0.72
    VALUE
    -0.67
    м
    -0.65
    Mit
    -0.63
    calling
    -0.63
    bats
    -0.62
    acements
    -0.61
     Mehran
    -0.61
    together
    -0.59
    except
    -0.58
    POSITIVE LOGITS
     County
    0.92
     Heights
    0.87
     Lumpur
    0.83
     City
    0.82
    upid
    0.80
     Township
    0.79
    burgh
    0.79
    abama
    0.77
    erville
    0.77
     Rapids
    0.76
    Activations Density 0.161%

    No Known Activations