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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 2146
    Prev
    Next
    INDEX
    Explanations

    proper names, likely the name "Isaac"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Isaac" and associated prominence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    marked
    -0.92
    lain
    -0.88
    ĸļ
    -0.81
    olulu
    -0.79
    emonium
    -0.78
    efully
    -0.77
    eful
    -0.77
    ebook
    -0.76
    liness
    -0.74
    naire
    -0.73
    POSITIVE LOGITS
     Isaac
    0.90
     Newton
    0.88
    antine
    0.78
    imov
    0.75
     Lev
    0.74
     Hayes
    0.74
     Dixon
    0.73
     Hemp
    0.70
    hem
    0.69
     Clarke
    0.69
    Activations Density 0.017%

    No Known Activations