Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 7809
    Prev
    Next
    INDEX
    Explanations

    time-related phrases, specifically focusing on the concepts of "early on" and "later on"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time, particularly relating to "early on" and "later on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.70
    lez
    -0.69
    SCP
    -0.65
    Thirty
    -0.65
    HOU
    -0.65
    CLOSE
    -0.60
    usterity
    -0.59
    ð
    -0.59
    pmwiki
    -0.59
    utenberg
    -0.59
    POSITIVE LOGITS
     onwards
    0.81
    .
    0.66
     glance
    0.65
    .(
    0.64
     thereafter
    0.62
    itiz
    0.61
     when
    0.61
    ounds
    0.60
    .}
    0.59
    forth
    0.58
    Activations Density 0.200%

    No Known Activations