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. 3-RES-JB
    6. 14090
    Prev
    Next
    INDEX
    Explanations

    characters and terms related to extended durations or periods

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "extended."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    士
    -0.81
    Hide
    -0.78
    é¾įåĸļ士
    -0.76
    âĸĪâĸĪâĸĪâĸĪ
    -0.75
    fighter
    -0.74
    zo
    -0.74
    powder
    -0.73
    mir
    -0.72
    Die
    -0.69
    Else
    -0.69
    POSITIVE LOGITS
     adolesc
    1.07
     extended
    0.87
     extensions
    0.85
     therap
    0.84
     warranties
    0.82
     satell
    0.82
     periods
    0.80
     Extended
    0.78
     maturity
    0.77
     confir
    0.77
    Activations Density 0.010%

    No Known Activations