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. 3452
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a suggestion or decision

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "just" in various contexts

    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
     Palestin
    -0.68
     challeng
    -0.64
    ccording
    -0.62
     Archdemon
    -0.60
     Strategies
    -0.59
    der
    -0.59
     subsequ
    -0.59
     Remastered
    -0.58
    Development
    -0.57
    rey
    -0.57
    POSITIVE LOGITS
    ifiable
    1.19
    ifications
    1.07
    ify
    0.94
    if
    0.94
    ification
    0.94
     ignore
    0.92
    ified
    0.91
    ifi
    0.87
     plain
    0.85
    ifiers
    0.83
    Activations Density 0.093%

    No Known Activations