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. 0-RES-JB
    6. 10713
    Prev
    Next
    INDEX
    Explanations

    phrases related to handling tasks or situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "handled" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     longing
    -0.62
    ãĤ¯
    -0.61
     inspiration
    -0.60
     Suggest
    -0.60
     warning
    -0.59
    arian
    -0.59
     deficit
    -0.59
    asm
    -0.59
     Claim
    -0.58
     Links
    -0.58
    POSITIVE LOGITS
     handled
    3.56
    handled
    2.02
     handles
    1.77
     dealt
    1.68
     mishand
    1.49
     handle
    1.48
     treated
    1.42
     solved
    1.34
     performed
    1.33
     tackled
    1.31
    Activations Density 0.012%

    No Known Activations