© 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. 1890
    Prev
    Next
    INDEX
    Explanations

    spokespersons or representatives in news articles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of spokespersons or representatives confirming statements

    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
    ãĤ¦ãĤ¹
    -0.80
    pieces
    -0.68
    Synopsis
    -0.68
     importantly
    -0.67
    entry
    -0.67
    ptions
    -0.66
     gamble
    -0.64
    Abstract
    -0.62
    Desktop
    -0.62
    iphate
    -0.62
    POSITIVE LOGITS
     Gov
    1.01
     Attorney
    0.85
     Mayor
    0.80
     Tourism
    0.79
     Metropolitan
    0.78
     Agriculture
    0.77
     spokesman
    0.77
     Concern
    0.76
     spokesperson
    0.76
     Senator
    0.75
    Activations Density 0.126%

    No Known Activations