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. 9-RES-JB
    6. 830
    Prev
    Next
    INDEX
    Explanations

    phrases related to gradual change or repetition / emphasis

    oai_token-act-pair · gpt-3.5-turbo

    commas and phrases indicating gradual change or evolution over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assi
    -0.75
    USS
    -0.68
    ãĤ¦ãĤ¹
    -0.65
    uge
    -0.62
    Ĺ
    -0.60
    ħĭ
    -0.60
    ãĥ£
    -0.59
    cluded
    -0.59
    ibles
    -0.58
    heim
    -0.58
    POSITIVE LOGITS
    without
    0.95
     without
    0.95
     preferably
    0.92
     cheaply
    0.89
     irrespective
    0.88
     orally
    0.81
     thanks
    0.81
     uninterrupted
    0.79
     anytime
    0.79
     during
    0.79
    Activations Density 0.445%

    No Known Activations