© 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. 6-RES-JB
    11. 1491
    Prev
    Next
    INDEX
    Explanations

    terms related to geographic locations specified with a "-based" prefix

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a geographic or organizational origin

    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
    alid
    -0.76
    dimension
    -0.74
    osure
    -0.73
    ν
    -0.71
    osen
    -0.69
    saf
    -0.69
    heart
    -0.67
    idences
    -0.67
    inges
    -0.67
    spir
    -0.67
    POSITIVE LOGITS
    quartered
    1.17
     entrepreneur
    0.88
     businessman
    0.85
     freelance
    0.82
     filmmaker
    0.81
     photographer
    0.78
     nonprofit
    0.77
     resident
    0.77
     artist
    0.74
     activist
    0.72
    Activations Density 0.029%

    No Known Activations