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. 10-RES-JB
    6. 15170
    Prev
    Next
    INDEX
    Explanations

    physical actions or states related to conflict or confrontation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional and physical struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     predec
    -0.60
     jurisd
    -0.59
    elve
    -0.57
     redes
    -0.56
    ãĥ¼ãĥĨãĤ£
    -0.55
    athered
    -0.54
    irteen
    -0.52
    anche
    -0.52
    ãĤ»
    -0.51
     comprehensive
    -0.51
    POSITIVE LOGITS
     lol
    1.23
     haha
    1.17
     doesnt
    1.14
     etc
    1.10
    ↵Âł
    1.09
     ;)
    1.07
     alot
    1.07
     dont
    1.06
     :)
    1.04
    !!!!
    1.02
    Activations Density 1.015%

    No Known Activations