© 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. 12-RES-JB
    11. 3465
    Prev
    Next
    INDEX
    Explanations

    phrases related to military conflicts and political tensions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to levels of scrutiny or evaluation concerning significant issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    zag
    -0.69
    sbm
    -0.64
    tered
    -0.64
    FORM
    -0.64
    vik
    -0.62
    nar
    -0.62
    finding
    -0.60
     Lack
    -0.60
     swayed
    -0.59
    jong
    -0.58
    POSITIVE LOGITS
     eyebrows
    1.21
     eyebrow
    1.09
     stakes
    1.03
     ire
    1.02
     ante
    1.02
     alarm
    1.00
     spect
    0.96
     profile
    0.95
     alarms
    0.93
     curtain
    0.90
    Activations Density 0.153%

    No Known Activations