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. 1-RES-JB
    6. 24346
    Prev
    Next
    INDEX
    Explanations

    the term "ARP" at varying levels of relevance

    oai_token-act-pair · gpt-3.5-turbo

    references to specific programs and technologies, particularly in the context of financial aid and gaming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rodgers
    -0.75
    ä¿
    -0.72
     Chel
    -0.71
    اØ
    -0.70
     è£ı
    -0.69
     è£ıç
    -0.69
     Mum
    -0.69
     Notting
    -0.67
    à©
    -0.67
     Meadows
    -0.66
    POSITIVE LOGITS
    ARP
    1.00
    sonian
    0.88
    regate
    0.82
    FN
    0.81
    uncture
    0.80
    lain
    0.78
    pocket
    0.77
    RL
    0.74
    eer
    0.71
    pired
    0.70
    Activations Density 0.028%

    No Known Activations