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. 3-RES-JB
    6. 19794
    Prev
    Next
    INDEX
    Explanations

    words related to encouragement and motivation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to encouragement and promotion of positive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nanto
    -0.80
    angler
    -0.66
    abases
    -0.65
    entin
    -0.64
    mbuds
    -0.63
    erion
    -0.61
     Estimates
    -0.60
    tis
    -0.59
    atism
    -0.59
    thin
    -0.59
    POSITIVE LOGITS
     encourage
    0.79
     encourages
    0.77
     encouraged
    0.75
    wcs
    0.74
    imaru
    0.74
     discouraged
    0.73
    tale
    0.72
     encouraging
    0.69
    IBLE
    0.68
    GGGGGGGG
    0.68
    Activations Density 0.027%

    No Known Activations