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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 20010
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to significant historical events or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kidding
    -0.79
    nown
    -0.69
     teasp
    -0.69
    ļéĨĴ
    -0.67
    tml
    -0.66
    ÃĥÃĤ
    -0.65
     guess
    -0.65
     hyster
    -0.64
     horrend
    -0.63
    =]
    -0.63
    POSITIVE LOGITS
     Korra
    1.19
     Xiaomi
    1.19
     OnePlus
    1.17
     Jaune
    1.15
     SpaceX
    1.14
     Pyrrha
    1.14
     SCP
    1.06
     Naruto
    1.05
     Huawei
    1.04
     Canaver
    1.03
    Activations Density 2.227%

    No Known Activations