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. 15757
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or official titles such as "Magistrate" or "Mag"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Magistrate."

    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
    ãģį
    -1.04
    OPLE
    -0.95
    éĹĺ
    -0.75
    INGTON
    -0.68
    ãĤĤ
    -0.68
     Rockefeller
    -0.68
     Hurricanes
    -0.67
     kHz
    -0.65
     Siem
    -0.65
    ãģ¯
    -0.65
    POSITIVE LOGITS
    istrate
    1.47
    istrates
    1.39
    nesium
    1.32
    ikarp
    1.31
    azines
    1.28
    netic
    1.21
    ento
    1.07
    pie
    1.06
    enta
    1.04
    lia
    1.01
    Activations Density 0.015%

    No Known Activations