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. 14590
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and business, especially in the context of enterprise operations

    oai_token-act-pair · gpt-3.5-turbo

    references to enterprise-related terms and 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
    abul
    -0.87
     Cabrera
    -0.86
    iggurat
    -0.79
    ificent
    -0.78
    inus
    -0.78
    ĸļ
    -0.77
    terness
    -0.75
    andum
    -0.73
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.71
    ouf
    -0.70
    POSITIVE LOGITS
     versions
    1.15
     mode
    1.10
     editions
    1.06
     counterparts
    1.02
     modes
    0.99
     equivalents
    0.98
     gamers
    0.97
     oriented
    0.97
     gaming
    0.97
     formats
    0.95
    Activations Density 0.445%

    No Known Activations