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. 6-RES-JB
    6. 21663
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific names related to different fields like sports, technology, and entertainment

    oai_token-act-pair · gpt-3.5-turbo

    empty tokens or whitespace

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.60
    acebook
    -0.58
    apego
    -0.56
    milo
    -0.56
    urat
    -0.56
    oaded
    -0.54
    Tags
    -0.53
     Mermaid
    -0.52
    rehensive
    -0.51
    uilt
    -0.50
    POSITIVE LOGITS
     nutshell
    0.76
     context
    0.68
     circles
    0.63
     guise
    0.63
     vicinity
    0.58
     mode
    0.58
     area
    0.57
     hurry
    0.56
     COURT
    0.54
     midst
    0.53
    Activations Density 0.670%

    No Known Activations