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. 4934
    Prev
    Next
    INDEX
    Explanations

    words related to transformation or change

    oai_token-act-pair · gpt-3.5-turbo

    technical terminology related to mechanics and structural components

    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
     Immunity
    -0.76
     Kills
    -0.75
     Wilde
    -0.69
     Elves
    -0.66
     Reach
    -0.63
     Reborn
    -0.62
    enegger
    -0.61
     Aires
    -0.60
     Pell
    -0.60
     Span
    -0.60
    POSITIVE LOGITS
    ruction
    1.28
    anced
    1.05
    alog
    1.01
    tenance
    1.00
    acters
    0.98
    secut
    0.97
    ipment
    0.96
    roying
    0.95
    yright
    0.94
    ition
    0.94
    Activations Density 0.173%

    No Known Activations