© 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. 12912
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to personal names or locations

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly those related to family and notable individuals

    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
    detail
    -0.72
    depending
    -0.71
    since
    -0.70
     unfocusedRange
    -0.67
    Besides
    -0.67
    have
    -0.66
    ertain
    -0.64
     FY
    -0.64
    Considering
    -0.63
     Recent
    -0.63
    POSITIVE LOGITS
     arrived
    1.06
     invaded
    1.02
     died
    1.02
     walked
    1.01
     entered
    1.00
     stepped
    1.00
     approached
    0.99
     abruptly
    0.99
     disappeared
    0.99
     visited
    0.98
    Activations Density 0.233%

    No Known Activations