© 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. 1208
    Prev
    Next
    INDEX
    Explanations

    verbs related to intense scrutiny, focus or examination

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to resolution or central themes in discussions or narratives

    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
    score
    -0.61
    adobe
    -0.60
    ingham
    -0.60
     surrendered
    -0.57
     helicop
    -0.57
    antha
    -0.57
     scrambled
    -0.56
     sacrificed
    -0.56
    IBLE
    -0.55
     snapped
    -0.55
    POSITIVE LOGITS
     principally
    0.95
     solely
    0.94
     mainly
    0.93
     primarily
    0.93
     chiefly
    0.88
     specifically
    0.87
     loosely
    0.85
    actionDate
    0.85
     exclusively
    0.82
    yrinth
    0.79
    Activations Density 0.125%

    No Known Activations