© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 11-RES-JB
    11. 12886
    Prev
    Next
    INDEX
    Explanations

    words related to geology and earth sciences

    oai_token-act-pair · gpt-3.5-turbo

    words with suffixes typically associated with scientific or technical terminology

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    cedented
    -0.86
    MED
    -0.80
    bourg
    -0.77
    ãģ®éŃĶ
    -0.76
    paid
    -0.75
    better
    -0.73
    matched
    -0.73
    bsite
    -0.72
    actual
    -0.72
    nah
    -0.71
    POSITIVE LOGITS
    ity
    1.20
    ism
    1.04
    ities
    0.98
     tendencies
    0.98
    ists
    0.97
    ALLY
    0.94
    ization
    0.87
    ized
    0.84
    ist
    0.84
    isation
    0.82
    Activations Density 0.196%

    No Known Activations