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. 6025
    Prev
    Next
    INDEX
    Explanations

    verbs related to coming into contact or facing a particular situation or person

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "encounter" 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
    2020
    -0.73
    spons
    -0.63
    ä¼
    -0.61
    rug
    -0.60
    states
    -0.60
    aim
    -0.60
    simple
    -0.60
    john
    -0.60
    Nation
    -0.60
     gravy
    -0.59
    POSITIVE LOGITS
     encounter
    3.81
     encounters
    2.95
     encountering
    2.07
     Encounter
    2.04
     encountered
    1.87
     interaction
    1.57
     confrontation
    1.56
     encount
    1.55
     experience
    1.48
     interactions
    1.45
    Activations Density 0.013%

    No Known Activations