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. 22905
    Prev
    Next
    INDEX
    Explanations

    technical terms related to internet and networking

    oai_token-act-pair · gpt-3.5-turbo

    technical acronyms and codes related to networking and computing

    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
    à©
    -0.51
     Give
    -0.48
     woman
    -0.45
     Offline
    -0.44
     Ebola
    -0.44
     takeaway
    -0.44
     Take
    -0.43
     welcome
    -0.43
     stay
    -0.43
     pregnant
    -0.43
    POSITIVE LOGITS
    .).
    1.07
    $.
    1.00
    !.
    0.99
    ().
    0.96
    %.
    0.90
    _.
    0.89
    +.
    0.88
    }.
    0.87
     respectively
    0.87
    .]
    0.86
    Activations Density 0.818%

    No Known Activations