© 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. 11881
    Prev
    Next
    INDEX
    Explanations

    superlatives, emphasizing extreme qualities

    oai_token-act-pair · gpt-3.5-turbo

    phrases contrasting the attributes of different groups or individuals, emphasizing extremities or qualities

    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
     VIDEOS
    -0.87
    ournals
    -0.72
     Starts
    -0.70
     giveaways
    -0.67
    ageddon
    -0.66
     Moments
    -0.66
     Lessons
    -0.66
     Draw
    -0.65
     Weeks
    -0.65
    osate
    -0.64
    POSITIVE LOGITS
     talented
    1.45
     knowledgeable
    1.35
     gifted
    1.33
     skilled
    1.33
     educated
    1.32
     competent
    1.30
    educated
    1.27
     intelligent
    1.26
     experienced
    1.25
     wealthy
    1.25
    Activations Density 0.207%

    No Known Activations