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

    Neuronpedia

    APICircuit 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. 18301
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings or official documents containing the word "plaintiff"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "Pl" or variations of it, indicating a focus on certain labels or codes

    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
    âĸ¬âĸ¬
    -0.79
    âĸ¬
    -0.79
     nexus
    -0.62
     prom
    -0.62
     Mae
    -0.60
    worthiness
    -0.58
     rounding
    -0.57
     coll
    -0.57
     Siri
    -0.57
     FANTASY
    -0.56
    POSITIVE LOGITS
    umbing
    1.53
    utonium
    1.53
    ausible
    1.47
    acement
    1.46
    atinum
    1.45
    asma
    1.44
    enty
    1.39
    acid
    1.37
    astics
    1.37
    atoon
    1.37
    Activations Density 0.023%

    No Known Activations