© 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. 3383
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events, power struggles, and tactics

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

    instances of the word "advantage" and related terms signaling the action of taking advantage of situations or exploiting loopholes

    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
    kos
    -0.69
    enta
    -0.68
    heses
    -0.68
    eller
    -0.66
    gru
    -0.65
    aughtered
    -0.65
    OTAL
    -0.64
    ods
    -0.62
    cone
    -0.62
    arter
    -0.62
    POSITIVE LOGITS
     loopholes
    1.49
     opportunities
    1.33
     weaknesses
    1.26
     loophole
    1.24
     vulnerabilities
    1.18
     opportunity
    1.14
     strengths
    1.12
     advantages
    1.03
     weakness
    1.00
     favourable
    0.95
    Activations Density 0.234%

    No Known Activations