Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 491
    Prev
    Next
    INDEX
    Explanations

    phrases related to paths or journeys

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to various metaphoric "paths" or trajectories toward goals or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yz
    -0.80
    ocks
    -0.71
     pauses
    -0.71
     Held
    -0.70
    minus
    -0.69
     Commands
    -0.68
    worms
    -0.67
    iw
    -0.67
    nces
    -0.66
    lines
    -0.66
    POSITIVE LOGITS
     enlightenment
    1.33
     prosperity
    1.12
     madness
    1.10
     riches
    1.08
     glory
    1.07
     citizenship
    1.07
     salvation
    1.05
     victory
    1.04
     immortality
    1.04
     redemption
    1.04
    Activations Density 0.215%

    No Known Activations