© 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. 1-RES-JB
    11. 2484
    Prev
    Next
    INDEX
    Explanations

    mentions of events, locations, and technology related to a specific brand or company

    oai_token-act-pair · gpt-3.5-turbo

    the mention of the abbreviation "EM" related to events or competitions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    netflix
    -0.82
     Cab
    -0.72
     Sanford
    -0.70
     Alaska
    -0.70
     skirts
    -0.69
     Strauss
    -0.69
     Kubrick
    -0.68
     Sack
    -0.68
     Hollow
    -0.67
     Rica
    -0.66
    POSITIVE LOGITS
    ERG
    1.26
    BLE
    1.03
    igrants
    1.02
    EM
    0.99
    achine
    0.99
    EMS
    0.98
    phal
    0.96
    ILY
    0.96
    PT
    0.93
    isphere
    0.93
    Activations Density 0.005%

    No Known Activations