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. 4353
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication or information sharing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "word of mouth."

    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
    hire
    -0.76
    respective
    -0.72
    photo
    -0.65
    cycles
    -0.65
    neys
    -0.64
    ilial
    -0.64
    igi
    -0.64
    00200000
    -0.64
    rac
    -0.63
    erella
    -0.63
    POSITIVE LOGITS
     encouragement
    0.82
     Allah
    0.78
     caution
    0.75
     recommendation
    0.71
    mouth
    0.70
     advice
    0.70
     wisdom
    0.70
     mouth
    0.69
     Allaah
    0.68
     Cthulhu
    0.64
    Activations Density 0.071%

    No Known Activations