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. 11-RES-JB
    6. 23481
    Prev
    Next
    INDEX
    Explanations

    statements highlighting the positive aspects or advantages of a particular subject

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating benefits or positive aspects of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.76
    BuyableInstoreAndOnline
    -0.71
    Þ
    -0.71
    MpServer
    -0.69
    ocaust
    -0.61
    ĪĴ
    -0.61
    aukee
    -0.60
    ATIONS
    -0.60
     redes
    -0.60
    akh
    -0.59
    POSITIVE LOGITS
     unlike
    1.27
     it
    1.15
     whereas
    1.04
     whenever
    1.03
     they
    1.01
     although
    0.94
     you
    0.93
     once
    0.89
     nowadays
    0.86
     while
    0.85
    Activations Density 0.237%

    No Known Activations