© 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. 16349
    Prev
    Next
    INDEX
    Explanations

    HTML tags that signify the opening and closing of different sections or elements

    oai_token-act-pair · gpt-3.5-turbo

    HTML and XML tags or markup elements

    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
    ysis
    -0.79
     subdu
    -0.75
    itive
    -0.69
     favors
    -0.69
    ube
    -0.66
     locality
    -0.64
     proxies
    -0.63
     prevailing
    -0.62
    imes
    -0.62
     brutally
    -0.61
    POSITIVE LOGITS
    ><
    1.02
    ></
    0.99
    RESULTS
    0.94
    EStream
    0.92
    ][/
    0.84
    PAR
    0.83
     srfAttach
    0.83
    DIV
    0.80
    college
    0.78
    usr
    0.77
    Activations Density 0.008%

    No Known Activations