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. 16037
    Prev
    Next
    INDEX
    Explanations

    verbs and adjectives related to attributes or actions that are definitive or causative in some way

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    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
    ruct
    -0.73
    adelphia
    -0.64
    cess
    -0.64
     Radius
    -0.63
    ãĤ´ãĥ³
    -0.63
    ization
    -0.61
     Souls
    -0.60
    MSN
    -0.58
    iasco
    -0.57
     Warcraft
    -0.57
    POSITIVE LOGITS
     therefore
    1.29
     consequently
    1.27
     accordingly
    1.14
     thus
    0.96
     furthermore
    0.94
     thereby
    0.88
     subsequently
    0.79
     moreover
    0.78
     thereafter
    0.76
     consequ
    0.75
    Activations Density 0.205%

    No Known Activations