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. 21343
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant achievements or records in various fields

    oai_token-act-pair · gpt-3.5-turbo

    references to significant achievements or milestones in sports or entertainment

    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
    ................................................................
    -0.67
    catentry
    -0.63
    medium
    -0.61
    iquid
    -0.58
    eln
    -0.58
    DragonMagazine
    -0.57
    invoke
    -0.57
    resso
    -0.57
    little
    -0.56
     Simpl
    -0.56
    POSITIVE LOGITS
    owered
    0.84
     remotely
    0.78
    clusively
    0.73
     consecut
    0.72
     consecutive
    0.71
    tains
    0.68
    ukong
    0.66
     outright
    0.65
     criminally
    0.64
     anywhere
    0.64
    Activations Density 0.676%

    No Known Activations