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

    Neuronpedia

    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. 10-RES-JB
    11. 3012
    Prev
    Next
    INDEX
    Explanations

    names of reporters or journalists

    oai_token-act-pair · gpt-3.5-turbo

    instances of named individuals or reporters in news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    viation
    -0.63
     Reincarn
    -0.60
     Refuge
    -0.59
     promoters
    -0.58
    Supporters
    -0.58
     Jehovah
    -0.58
     Nur
    -0.57
     Ministers
    -0.57
     Cabinet
    -0.57
    Sold
    -0.57
    POSITIVE LOGITS
    column
    0.94
     reporting
    0.93
     (@
    0.92
     previews
    0.90
     investigates
    0.89
     podcast
    0.89
     headlined
    0.88
     contributed
    0.88
     Reporting
    0.87
    aminer
    0.87
    Activations Density 0.266%

    No Known Activations