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. 7-RES-JB
    6. 3416
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Rick"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names, particularly "Rick" and "Derrick."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asions
    -0.72
    atform
    -0.69
    itar
    -0.67
    amaz
    -0.66
    awar
    -0.65
     Mahar
    -0.64
    ihar
    -0.63
     epid
    -0.63
    ãĤ£
    -0.62
    ãĤ§
    -0.61
    POSITIVE LOGITS
    etts
    1.01
    ety
    0.89
    essee
    0.85
    ements
    0.83
    eering
    0.80
    uary
    0.75
    yers
    0.75
    heid
    0.72
    ett
    0.72
    haw
    0.72
    Activations Density 0.073%

    No Known Activations