© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 19307
    Prev
    Next
    INDEX
    Explanations

    phrases related to various states or conditions that a place, country, or world might be in

    oai_token-act-pair · gpt-3.5-turbo

    references to states of transition or crisis in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bribes
    -0.73
     compliment
    -0.67
     Helpful
    -0.66
     blunt
    -0.66
     staples
    -0.66
     anonymously
    -0.64
     Bene
    -0.64
     Insp
    -0.64
     nails
    -0.62
     flattering
    -0.62
    POSITIVE LOGITS
     brink
    0.97
     limbo
    0.95
     infancy
    0.87
    alysed
    0.85
     reckoning
    0.81
     mode
    0.81
     predicament
    0.81
     frenzy
    0.80
     phase
    0.80
     nightmare
    0.80
    Activations Density 0.461%

    No Known Activations