© 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. 11-RES-JB
    11. 17568
    Prev
    Next
    INDEX
    Explanations

    locations and events related to warfare and conflict

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and names related to conflict zones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CEOs
    -0.66
     crank
    -0.63
     SJ
    -0.62
     promoters
    -0.60
     detectives
    -0.60
     neo
    -0.60
     CEO
    -0.60
     pitchers
    -0.60
     railing
    -0.60
     narciss
    -0.59
    POSITIVE LOGITS
    qqa
    1.16
    arah
    1.05
    amiya
    1.00
    bil
    0.99
    raq
    0.98
    abul
    0.98
    area
    0.95
    iyah
    0.93
    ujah
    0.93
    myra
    0.92
    Activations Density 0.127%

    No Known Activations