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

    Neuronpedia

    APICircuit 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. 1-RES-JB
    6. 12406
    Prev
    Next
    INDEX
    Explanations

    references to giving or paying respects/tokens to someone or something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "tribute."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Niet
    -0.76
     Cot
    -0.72
    neck
    -0.68
     TSA
    -0.68
     latex
    -0.68
     resolution
    -0.67
     Schmidt
    -0.66
     BDS
    -0.63
     Cotton
    -0.63
     Outer
    -0.63
    POSITIVE LOGITS
    ribute
    1.33
    ributes
    1.31
    ribut
    1.24
    iosyncr
    1.16
    yip
    1.05
    ributed
    1.05
    ividual
    1.03
    ratulations
    1.02
    ribution
    1.01
    jri
    1.00
    Activations Density 0.019%

    No Known Activations