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. 13253
    Prev
    Next
    INDEX
    Explanations

    specific times mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    specific timestamps or numeric data formats, particularly in the context of events or reports

    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
    asons
    -0.65
    pring
    -0.61
    ocado
    -0.61
    \":
    -0.60
     ado
    -0.58
    bys
    -0.58
    farious
    -0.58
     scrut
    -0.58
    ²¾
    -0.56
    FontSize
    -0.55
    POSITIVE LOGITS
     partName
    0.86
     -->
    0.83
     Converted
    0.79
     @@
    0.77
     <[
    0.71
     INFO
    0.71
     Fiat
    0.67
     Info
    0.66
     <-
    0.63
     <+
    0.63
    Activations Density 0.073%

    No Known Activations