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. 8-RES-JB
    6. 20719
    Prev
    Next
    INDEX
    Explanations

    instances where multiple entities or concepts are described as being the same

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of sameness or shared characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ttes
    -0.89
    skirts
    -0.86
     Provided
    -0.85
    xtap
    -0.83
    zy
    -0.83
    flex
    -0.83
    usa
    -0.80
    itely
    -0.79
    rection
    -0.76
    bane
    -0.75
    POSITIVE LOGITS
     thing
    0.93
     basic
    0.85
     nationality
    0.82
     amount
    0.82
     sentence
    0.82
     wavelength
    0.81
     molecule
    0.81
     geographical
    0.81
     organism
    0.81
     exact
    0.80
    Activations Density 0.053%

    No Known Activations