© 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. 7797
    Prev
    Next
    INDEX
    Explanations

    instances of negative events or controversial actions related to individuals in various roles or positions

    oai_token-act-pair · gpt-3.5-turbo

    instances of post-resignation events or consequences

    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
    soDeliveryDate
    -0.75
    iour
    -0.73
     toget
    -0.70
     kings
    -0.69
    ipeg
    -0.68
     marqu
    -0.65
     Purg
    -0.65
    enfranch
    -0.64
    rieve
    -0.64
    inct
    -0.62
    POSITIVE LOGITS
     allegations
    1.16
     allegedly
    1.09
     mishand
    1.07
     violating
    1.05
     misconduct
    1.05
     breaching
    1.04
     violations
    1.03
     alleged
    1.02
     fals
    0.98
     accusations
    0.98
    Activations Density 0.205%

    No Known Activations