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. 10-RES-JB
    6. 22601
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-3.5-turbo

    connections or relationships in sentences, particularly those that involve expressions of unity or collaborative sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĥī
    -0.81
    pmwiki
    -0.78
    Contents
    -0.75
    otom
    -0.72
    Enlarge
    -0.72
    ãĥĺ
    -0.71
    toggle
    -0.71
    pron
    -0.69
    NetMessage
    -0.68
    verbal
    -0.65
    POSITIVE LOGITS
     appreciate
    1.15
     strive
    1.14
     we
    1.07
     intend
    1.07
     wish
    1.06
     welcomes
    1.03
     cherish
    1.02
     hope
    1.00
     strives
    0.99
     urge
    0.99
    Activations Density 0.230%

    No Known Activations