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. 21815
    Prev
    Next
    INDEX
    Explanations

    strings that contain acronyms and organizational terms such as military-related ones

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or codes related to military and organizational contexts

    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
     mater
    -0.71
    âĹ¼
    -0.67
     Sapphire
    -0.66
    adobe
    -0.66
    lain
    -0.66
    ifice
    -0.63
    eer
    -0.63
     Calder
    -0.59
     Boone
    -0.59
    upt
    -0.59
    POSITIVE LOGITS
    letcher
    1.13
    ornia
    1.05
    rozen
    1.01
    rost
    1.00
    ruits
    0.96
    ocused
    0.95
    iture
    0.94
    ISH
    0.93
    arlane
    0.89
    avorable
    0.88
    Activations Density 0.196%

    No Known Activations