© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 13722
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to web technology

    oai_token-act-pair · gpt-3.5-turbo

    references to the web or web-related technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unfocusedRange
    -0.86
    士
    -0.83
    20439
    -0.66
     sidx
    -0.66
    045
    -0.65
    å£
    -0.64
    âĸ
    -0.64
    âĶĢâĶĢ
    -0.63
     Clause
    -0.63
    é¾įå
    -0.62
    POSITIVE LOGITS
    pages
    1.06
    browser
    0.95
     browsers
    0.92
    inar
    0.89
     web
    0.87
     browser
    0.86
    izen
    0.86
    web
    0.85
     webs
    0.83
     analytics
    0.82
    Activations Density 0.012%

    No Known Activations