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. 16457
    Prev
    Next
    INDEX
    Explanations

    statements indicating lack of progress or stalling in a process or communication

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of communication-related concepts

    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
     Characters
    -0.65
     Truly
    -0.63
     aka
    -0.62
     embodies
    -0.60
    joice
    -0.60
     intrinsically
    -0.59
     wonderfully
    -0.58
     glamorous
    -0.57
     sexy
    -0.57
     truly
    -0.56
    POSITIVE LOGITS
     fax
    0.79
     subpoen
    0.76
     deadline
    0.75
     adjourn
    0.74
     jurisd
    0.70
     pending
    0.70
     deadlines
    0.69
     redacted
    0.68
     paperwork
    0.68
     postponed
    0.67
    Activations Density 1.290%

    No Known Activations