© 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. 11-RES-JB
    11. 22331
    Prev
    Next
    INDEX
    Explanations

    instances where someone has experience or knowledge in a certain subject

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals' experiences or identities

    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
     Subst
    -0.76
    interstitial
    -0.69
    auga
    -0.65
     Surprise
    -0.63
     Prompt
    -0.63
     Splash
    -0.62
     scorer
    -0.62
     Reloaded
    -0.61
     prompts
    -0.60
     guiName
    -0.60
    POSITIVE LOGITS
     studied
    1.18
     watched
    1.11
     interacted
    1.04
     frequ
    1.03
     worked
    1.02
     lived
    1.02
     attended
    1.01
     listened
    0.99
     convers
    0.95
     witnessed
    0.95
    Activations Density 0.249%

    No Known Activations