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. 3931
    Prev
    Next
    INDEX
    Explanations

    concern related phrases or expressions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "concern."

    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
     executed
    -0.69
    tops
    -0.64
     Drops
    -0.64
     executes
    -0.62
    utsch
    -0.61
    inside
    -0.61
    sung
    -0.60
    its
    -0.60
    agan
    -0.58
    insert
    -0.57
    POSITIVE LOGITS
     concern
    3.57
     Concern
    2.31
     concerns
    2.29
     worry
    2.07
     worries
    1.73
    cern
    1.66
     concerned
    1.60
     interest
    1.47
     fear
    1.41
     fears
    1.34
    Activations Density 0.018%

    No Known Activations