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. 8-RES-JB
    6. 5615
    Prev
    Next
    INDEX
    Explanations

    words related to positive social behavior, such as politeness, friendliness, and professionalism

    oai_token-act-pair · gpt-3.5-turbo

    descriptors of politeness and friendliness in interpersonal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     destro
    -0.80
    ãĥ¯ãĥ³
    -0.77
    massive
    -0.77
    ources
    -0.75
    project
    -0.73
    mega
    -0.73
    iaries
    -0.73
     Project
    -0.71
    士
    -0.70
     Inferno
    -0.70
    POSITIVE LOGITS
     greeting
    1.44
     polite
    1.30
     politely
    1.22
     greet
    1.19
     nodding
    1.19
     hugs
    1.18
     nods
    1.12
     smile
    1.12
     condesc
    1.12
     demeanor
    1.11
    Activations Density 0.772%

    No Known Activations