© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1249
    Prev
    Next
    INDEX
    Explanations

    phrases related to paths or ways to achieve something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe various "paths" or "routes" to achieving specific goals or outcomes

    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
     Held
    -0.76
    hot
    -0.72
    bryce
    -0.72
     Commands
    -0.70
    sbm
    -0.68
    lease
    -0.67
    minus
    -0.67
    forces
    -0.66
    amount
    -0.65
    ennis
    -0.65
    POSITIVE LOGITS
     enlightenment
    1.26
     madness
    1.03
     Enlightenment
    0.97
     victory
    0.96
     glory
    0.96
     prosperity
    0.96
     riches
    0.95
     citizenship
    0.95
     exhaustion
    0.93
     immortality
    0.92
    Activations Density 0.195%

    No Known Activations