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. 16255
    Prev
    Next
    INDEX
    Explanations

    phrases related to the handling or management of various tasks or situations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "handling."

    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
    atl
    -0.69
     Prosper
    -0.67
    nova
    -0.67
    oiler
    -0.66
    atu
    -0.64
     Fallen
    -0.63
     Borg
    -0.63
     Jihad
    -0.62
    ren
    -0.61
    ç
    -0.61
    POSITIVE LOGITS
     handling
    3.87
     Handling
    2.82
     mishand
    1.87
     handled
    1.82
     handle
    1.68
     handles
    1.63
     processing
    1.49
     dealing
    1.49
     handlers
    1.40
     handler
    1.35
    Activations Density 0.030%

    No Known Activations