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. 14877
    Prev
    Next
    INDEX
    Explanations

    numbers or terms related to deadlines or time constraints

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to updates and notifications across various topics

    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
    sbm
    -0.86
    é¾įåĸļ士
    -0.82
    âĹ¼
    -0.81
    ÙIJ
    -0.77
    ãģĨ
    -0.75
     Athletic
    -0.72
    POSE
    -0.71
    perty
    -0.70
    Integer
    -0.70
    Slot
    -0.69
    POSITIVE LOGITS
     begins
    0.90
     overview
    0.88
     looms
    0.88
     replaces
    0.87
     info
    0.85
     survives
    0.85
     awaits
    0.85
     opens
    0.84
     sparks
    0.84
     includes
    0.84
    Activations Density 0.318%

    No Known Activations