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. 22545
    Prev
    Next
    INDEX
    Explanations

    phrases containing "day-to-day" or related expressions

    oai_token-act-pair · gpt-3.5-turbo

    the concept of day-to-day experiences or routines

    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
     Borders
    -0.76
     Si
    -0.71
     Compass
    -0.67
     Saunders
    -0.66
     Ic
    -0.66
     Mechdragon
    -0.63
     Ri
    -0.62
     BB
    -0.61
     Tec
    -0.61
     Confederation
    -0.61
    POSITIVE LOGITS
    to
    1.24
    sized
    1.14
    appropriate
    1.13
    by
    1.12
    long
    1.10
    specific
    1.10
    time
    1.05
    wise
    1.03
    trip
    1.03
    of
    1.01
    Activations Density 0.031%

    No Known Activations