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. 19799
    Prev
    Next
    INDEX
    Explanations

    the name "Ronaldini"

    oai_token-act-pair · gpt-3.5-turbo

    instances of a particular name or phrase related to a person

    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
    ĻĤ
    -0.75
    ¥µ
    -0.74
    worthy
    -0.72
    pages
    -0.70
    steps
    -0.67
    friends
    -0.67
    names
    -0.65
    ¥
    -0.64
    groups
    -0.63
     soph
    -0.61
    POSITIVE LOGITS
    ini
    1.30
    etta
    0.89
    etti
    0.89
    otto
    0.87
    zzle
    0.87
    otti
    0.86
    ptin
    0.85
    emi
    0.83
    igne
    0.83
    eta
    0.83
    Activations Density 0.004%

    No Known Activations