© 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. 10232
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific phrases related to titles or names

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express relationships and attribution

    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
     Lines
    -0.60
    soDeliveryDate
    -0.59
     Costs
    -0.58
     IMAGES
    -0.58
     HAS
    -0.57
    has
    -0.57
     REAL
    -0.57
     installations
    -0.56
     stru
    -0.56
     lines
    -0.55
    POSITIVE LOGITS
     contend
    1.17
     choose
    1.13
    wered
    1.05
    ggles
    1.03
    pload
    0.97
     fill
    0.94
     accommodate
    0.94
     accompany
    0.93
     satisfy
    0.92
     emulate
    0.90
    Activations Density 0.142%

    No Known Activations