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. 6-RES-JB
    6. 19551
    Prev
    Next
    INDEX
    Explanations

    action verbs related to performing tasks or taking action

    oai_token-act-pair · gpt-3.5-turbo

    action verbs that suggest taking initiative or making changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.83
     respectively
    -0.62
     Jur
    -0.57
     Glob
    -0.55
     wont
    -0.55
    vernight
    -0.53
     marked
    -0.52
     Sect
    -0.51
    ItemTracker
    -0.51
     resulting
    -0.50
    POSITIVE LOGITS
     oneself
    1.21
     ourselves
    0.89
    uate
    0.86
     yourself
    0.86
    itate
    0.84
    enance
    0.81
    ulate
    0.80
    iate
    0.78
     yourselves
    0.77
    dule
    0.70
    Activations Density 0.481%

    No Known Activations