Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 23580
    Prev
    Next
    INDEX
    Explanations

    terms related to computer programming, system setup instructions, and code structure

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to programming and coding instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Others
    -0.87
    Fax
    -0.78
    Elsewhere
    -0.77
     Others
    -0.75
    else
    -0.74
    better
    -0.73
     reconsider
    -0.71
    rosso
    -0.71
    Other
    -0.69
     latter
    -0.67
    POSITIVE LOGITS
     basic
    0.84
     basics
    0.80
     premise
    0.76
     randomly
    0.75
    Basic
    0.74
     initialize
    0.74
     consists
    0.72
     integers
    0.71
    Setup
    0.70
     rectangular
    0.69
    Activations Density 0.624%

    No Known Activations