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. 11389
    Prev
    Next
    INDEX
    Explanations

    phrases related to timing and spatial orientation

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to timing, placement, and degree of quantities

    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
    xtap
    -0.74
    this
    -0.72
    ovember
    -0.72
    Alan
    -0.71
    ntil
    -0.70
    THIS
    -0.69
     helicop
    -0.69
    oan
    -0.68
    trak
    -0.68
    rex
    -0.68
    POSITIVE LOGITS
     colours
    0.79
     gadgets
    0.75
     ones
    0.73
     colors
    0.71
     wallets
    0.71
     budgets
    0.68
     profit
    0.68
     coloured
    0.68
     budget
    0.67
     amount
    0.66
    Activations Density 0.387%

    No Known Activations