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. 5283
    Prev
    Next
    INDEX
    Explanations

    sentences related to software development or coding practice

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    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
     pul
    -0.74
    plet
    -0.72
    amn
    -0.69
     imperson
    -0.68
    eteen
    -0.63
    tain
    -0.62
    gment
    -0.61
    lined
    -0.61
    vil
    -0.60
    ilion
    -0.60
    POSITIVE LOGITS
     Lastly
    1.82
     Finally
    1.68
     Conversely
    1.43
     Similarly
    1.42
     Likewise
    1.36
     Furthermore
    1.35
     Ultimately
    1.34
     Alternatively
    1.31
    Finally
    1.29
     Nevertheless
    1.29
    Activations Density 0.636%

    No Known Activations