© 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. 9-RES-JB
    11. 15495
    Prev
    Next
    INDEX
    Explanations

    countries, names of people, and events related to competitions and championships

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant achievements or milestones in sports history

    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
    asonable
    -0.88
    inventoryQuantity
    -0.85
     Concern
    -0.85
    soType
    -0.83
    politics
    -0.83
    addons
    -0.83
     paranoia
    -0.80
     Worse
    -0.75
     distrust
    -0.75
     skepticism
    -0.73
    POSITIVE LOGITS
     feat
    1.18
     exce
    1.10
     selfie
    1.08
     scored
    1.06
     feats
    1.05
     showcased
    1.04
     outper
    1.04
     strut
    1.03
     medal
    1.01
     participated
    1.01
    Activations Density 0.764%

    No Known Activations