© 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 EvalsExportsinterp-engineNEWAPI 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. 12199
    Prev
    Next
    INDEX
    Explanations

    instances where two entities are in opposing or competitive situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of competition or rivalry between individuals or groups

    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
     shortages
    -0.83
    arium
    -0.72
    Reader
    -0.69
    iries
    -0.65
    achers
    -0.65
    erved
    -0.64
    etch
    -0.64
    stadt
    -0.63
    elight
    -0.61
    vard
    -0.60
    POSITIVE LOGITS
     insepar
    0.87
     mutual
    0.70
     mutually
    0.69
    EStream
    0.66
    Ò
    0.65
     hashing
    0.65
    aukee
    0.64
    antically
    0.64
    ;;;;;;;;;;;;
    0.64
     Emacs
    0.63
    Activations Density 0.694%

    No Known Activations