© 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. 15703
    Prev
    Next
    INDEX
    Explanations

    phrases related to destruction and conflict

    oai_token-act-pair · gpt-3.5-turbo

    references to ancient or mythical deities and concepts of destruction or rebirth

    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
     interacting
    -0.79
     frequ
    -0.77
     interactions
    -0.74
     affinity
    -0.74
     frequent
    -0.73
     outreach
    -0.72
     regularly
    -0.70
     researching
    -0.69
     sourcing
    -0.69
     attachments
    -0.68
    POSITIVE LOGITS
     triumphant
    1.09
     forever
    1.07
    livion
    1.06
     victorious
    1.01
     triumph
    0.98
     losers
    0.98
     vind
    0.96
     vict
    0.91
     eternity
    0.90
     loser
    0.88
    Activations Density 0.955%

    No Known Activations