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. 10-RES-JB
    6. 7623
    Prev
    Next
    INDEX
    Explanations

    numerical values related to time

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numerical values, especially those related to time durations

    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
    channelAvailability
    -0.67
     likeness
    -0.66
     resemblance
    -0.64
    artisan
    -0.63
     leve
    -0.63
    brow
    -0.62
     leveled
    -0.62
     foremost
    -0.61
     uniqueness
    -0.61
    winner
    -0.58
    POSITIVE LOGITS
     hours
    1.69
     minutes
    1.63
    hours
    1.60
     seconds
    1.53
     hrs
    1.52
     days
    1.46
    seconds
    1.43
     Hours
    1.38
     mins
    1.35
    mins
    1.34
    Activations Density 0.124%

    No Known Activations