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. 22908
    Prev
    Next
    INDEX
    Explanations

    specific references to various events and places, potentially related to the year 2012

    oai_token-act-pair · gpt-3.5-turbo

    references to specific events or significant instances

    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
    SPONSORED
    -0.87
     else
    -0.76
    ency
    -0.75
    else
    -0.72
     another
    -0.70
    ery
    -0.69
     besides
    -0.68
    ride
    -0.68
     accompl
    -0.65
    package
    -0.64
    POSITIVE LOGITS
     ones
    1.57
     aforementioned
    1.21
     Ones
    0.97
     infamous
    0.92
     dreaded
    0.83
     likes
    0.79
     Kardash
    0.78
     occasional
    0.76
     Dalai
    0.72
     ubiquitous
    0.71
    Activations Density 0.255%

    No Known Activations