© 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. 12447
    Prev
    Next
    INDEX
    Explanations

    phrases related to political actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental policies and actions

    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
    irlf
    -0.73
    apses
    -0.69
    important
    -0.68
    acers
    -0.68
    udi
    -0.67
     impacting
    -0.66
    flies
    -0.65
    things
    -0.64
     deserve
    -0.64
     deserves
    -0.63
    POSITIVE LOGITS
     cautious
    1.05
     minimalist
    0.99
     posture
    0.97
     rigid
    0.94
     simplistic
    0.93
     strict
    0.92
     stance
    0.92
     regimen
    0.92
     reliance
    0.90
     approach
    0.88
    Activations Density 0.320%

    No Known Activations