© 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. 18508
    Prev
    Next
    INDEX
    Explanations

    phrases related to individuals being active on social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    references to freelance writers and their social media profiles

    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
    catentry
    -0.66
    âĢ¦âĢ¦âĢ¦âĢ¦
    -0.64
    Oracle
    -0.63
    HOU
    -0.63
     GOODMAN
    -0.63
    Tax
    -0.62
    pedia
    -0.61
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.61
     Soros
    -0.60
    INTON
    -0.60
    POSITIVE LOGITS
     IGN
    1.06
    IGN
    0.98
    Steam
    0.63
     Dota
    0.62
    Exit
    0.61
     mech
    0.60
     chats
    0.60
     sprite
    0.60
     dudes
    0.60
     Fighter
    0.59
    Activations Density 0.096%

    No Known Activations