© 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. 6-RES-JB
    6. 17159
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations, particularly states, and discussions related to them

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations, particularly states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    poons
    -1.05
    imet
    -0.87
    eatures
    -0.77
    thora
    -0.77
    iasco
    -0.74
    odiac
    -0.74
    ogle
    -0.73
    alore
    -0.73
    ikarp
    -0.73
    hift
    -0.72
    POSITIVE LOGITS
     legislatures
    0.89
    wide
    0.76
     Lutheran
    0.71
     Universities
    0.66
     governments
    0.65
     capitals
    0.64
     legalized
    0.63
     ACLU
    0.63
     nationals
    0.63
    gary
    0.62
    Activations Density 0.044%

    No Known Activations