© 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. 9-RES-JB
    11. 24262
    Prev
    Next
    INDEX
    Explanations

    terms related to cooperation and teamwork

    oai_token-act-pair · gpt-3.5-turbo

    repeated conjunctions in complex sentence structures

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ãĤ´ãĥ³
    -0.89
    !:
    -0.67
     ®
    -0.65
    hered
    -0.63
    leon
    -0.63
     Released
    -0.62
    pmwiki
    -0.61
    !--
    -0.61
    .*
    -0.60
    orno
    -0.59
    POSITIVE LOGITS
     stuff
    1.16
     everybody
    1.14
     blah
    1.11
     somebody
    1.03
     yeah
    0.99
    romeda
    0.97
     hopefully
    0.95
     I
    0.92
     frankly
    0.91
     âĢ¦"
    0.90
    Activations Density 0.260%

    No Known Activations