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. 10-RES-JB
    6. 9702
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "first" or phrases related to being the first of its kind or in a series

    oai_token-act-pair · gpt-3.5-turbo

    instances of something being labeled as "the first" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riber
    -0.72
    apters
    -0.72
    ractor
    -0.64
    iolet
    -0.63
    urities
    -0.62
    asions
    -0.60
    rs
    -0.60
    ourning
    -0.60
    lov
    -0.60
    iane
    -0.60
    POSITIVE LOGITS
     foray
    1.01
     indication
    0.93
     ever
    0.93
     casualty
    0.92
     step
    0.90
     tangible
    0.89
     thing
    0.88
     installment
    0.85
     major
    0.84
     truly
    0.83
    Activations Density 0.075%

    No Known Activations