© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18246
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or events

    oai_token-act-pair · gpt-3.5-turbo

    sentences and phrases that indicate reports or statements related to incidents or events

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     exha
    -0.83
     undermin
    -0.78
     councill
    -0.74
    £ı
    -0.74
    bryce
    -0.73
    mbuds
    -0.73
    byss
    -0.68
    ataka
    -0.68
     hitherto
    -0.64
     surplus
    -0.64
    POSITIVE LOGITS
    JUST
    1.46
    CNN
    1.22
    Photos
    1.14
     CNN
    0.96
     Replay
    0.94
    Media
    0.80
    BBC
    0.75
     IMAGES
    0.75
    NPR
    0.75
    "...
    0.74
    Activations Density 0.291%

    No Known Activations