© 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. 3098
    Prev
    Next
    INDEX
    Explanations

    words related to politics, conflicts, and international affairs

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

    content related to political events and social 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
     è£ıè
    -0.71
     hears
    -0.69
     conducts
    -0.68
     Uses
    -0.67
    Recomm
    -0.65
    âĶĢâĶĢâĶĢâĶĢ
    -0.65
     learns
    -0.64
     expects
    -0.64
     spends
    -0.64
     sleeps
    -0.62
    POSITIVE LOGITS
     were
    1.26
     weren
    1.20
     have
    1.18
     illustrate
    1.09
    have
    1.07
    were
    1.07
     culminated
    1.06
     indicate
    1.05
     haven
    1.05
     underscore
    1.05
    Activations Density 0.386%

    No Known Activations