© 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. 1-RES-JB
    11. 14560
    Prev
    Next
    INDEX
    Explanations

    references to the Census Bureau in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the Census Bureau

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arching
    -0.72
    erm
    -0.72
    unction
    -0.72
    practice
    -0.69
    andem
    -0.67
    ife
    -0.66
    amina
    -0.66
    ournals
    -0.65
    sterdam
    -0.63
    gettable
    -0.63
    POSITIVE LOGITS
     census
    1.01
     Census
    1.01
     tracts
    0.96
     tract
    0.87
     Bureau
    0.85
    ãĥ¼ãĥĨãĤ£
    0.82
    ãĤ¼ãĤ¦ãĤ¹
    0.80
    naire
    0.78
    ãĤº
    0.76
     Explorer
    0.73
    Activations Density 0.003%

    No Known Activations