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. 2124
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Anna"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "anna."

    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
    matically
    -1.06
    matical
    -0.95
     skelet
    -0.89
    lycer
    -0.88
    tle
    -0.83
    matic
    -0.82
     carbohyd
    -0.80
    mate
    -0.79
    lasses
    -0.79
    uid
    -0.78
    POSITIVE LOGITS
     Mae
    0.82
    isance
    0.82
    jac
    0.76
    emia
    0.76
    uthor
    0.76
    jo
    0.74
    ACP
    0.73
    anna
    0.73
    ë
    0.72
     Devi
    0.71
    Activations Density 0.019%

    No Known Activations