© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 12222
    Prev
    Next
    INDEX
    Explanations

    names and mentions of newspapers

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent newspapers and media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.85
    sed
    -0.70
    NetMessage
    -0.68
    tumblr
    -0.62
    animate
    -0.61
    atically
    -0.61
    ventus
    -0.60
    orate
    -0.59
     guiActiveUnfocused
    -0.59
    angular
    -0.59
    POSITIVE LOGITS
     reported
    1.52
     reports
    1.36
     understands
    1.23
     quoted
    1.20
     obtained
    1.17
     noted
    1.13
    reports
    1.13
     revealed
    1.10
     ran
    1.09
     learned
    1.09
    Activations Density 0.124%

    No Known Activations