© 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. 15767
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflicts involving two opposing sides

    oai_token-act-pair · gpt-3.5-turbo

    references to opposing parties or factions involved in a conflict

    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
    pta
    -0.74
    nce
    -0.73
    Delivery
    -0.60
    ķ
    -0.60
     Rapids
    -0.60
    awar
    -0.57
    rupted
    -0.57
     Miko
    -0.57
    DERR
    -0.57
    venient
    -0.56
    POSITIVE LOGITS
     alike
    1.06
     equally
    1.00
     mutually
    0.97
     simultaneously
    0.96
     sides
    0.96
     sexes
    0.96
     vying
    0.88
    emate
    0.85
     agree
    0.85
    '
    0.83
    Activations Density 0.175%

    No Known Activations