© 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. 8-RES-JB
    11. 11898
    Prev
    Next
    INDEX
    Explanations

    mentions of specific dates or time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to television episodes and their specific content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vou
    -0.74
     moreover
    -0.61
     furthermore
    -0.61
     coerc
    -0.60
     behav
    -0.57
    åĮ
    -0.56
     cultivated
    -0.56
     therefore
    -0.56
    gerald
    -0.56
     disadvant
    -0.55
    POSITIVE LOGITS
     countdown
    0.79
     fireworks
    0.76
    reetings
    0.76
    Reviewer
    0.74
     festivities
    0.73
     celebration
    0.72
     adjourn
    0.71
     livestream
    0.70
     Recap
    0.69
     Celebration
    0.68
    Activations Density 1.555%

    No Known Activations