© 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. 0-RES-JB
    11. 9586
    Prev
    Next
    INDEX
    Explanations

    mentions of different sides involved in a conflict or negotiation

    oai_token-act-pair · gpt-3.5-turbo

    references to opposing factions or viewpoints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vich
    -0.70
    ptive
    -0.63
    Bio
    -0.62
    brance
    -0.60
    iami
    -0.60
    kai
    -0.59
    umo
    -0.59
    naire
    -0.59
    utor
    -0.59
    uchin
    -0.57
    POSITIVE LOGITS
     sides
    4.04
     side
    2.14
     halves
    1.49
     Side
    1.42
    side
    1.41
     corners
    1.40
    sided
    1.39
     fronts
    1.38
     sexes
    1.34
    Side
    1.32
    Activations Density 0.011%

    No Known Activations