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. 22190
    Prev
    Next
    INDEX
    Explanations

    the letter "z" followed by a word or part of a word

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'z'

    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
    •words starting with z

    No Comments

    Negative Logits
    tenance
    -0.71
     Palestin
    -0.71
    ModLoader
    -0.71
    mingham
    -0.70
     compe
    -0.70
     Sut
    -0.69
     Lumpur
    -0.69
     Staples
    -0.68
     disadvant
    -0.68
     Lauder
    -0.66
    POSITIVE LOGITS
    ebra
    1.30
    eros
    1.17
    ooming
    1.14
    ipped
    1.11
    odiac
    1.09
    ither
    1.07
    ipping
    1.06
    ippers
    1.05
    ipper
    1.04
    ipp
    1.01
    Activations Density 0.015%

    No Known Activations