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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 12498
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Casper"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Cas" in various contexts

    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
    doms
    -0.85
    çīĪ
    -0.79
    uyomi
    -0.78
     nomine
    -0.74
    ĺħ
    -0.70
    ħĭ
    -0.69
     guiActiveUn
    -0.69
    ĪĴ
    -0.69
    ¥ŀ
    -0.69
    ãģķ
    -0.64
    POSITIVE LOGITS
    imir
    1.24
    nell
    0.98
    illas
    0.96
    illo
    0.95
    anova
    0.94
    abl
    0.93
    atell
    0.93
    arella
    0.92
    bah
    0.88
    hew
    0.88
    Activations Density 0.012%

    No Known Activations