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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 9729
    Prev
    Next
    INDEX
    Explanations

    phrases related to a significant duration of time

    oai_token-act-pair · gpt-3.5-turbo

    references to prolonged durations of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tro
    -0.72
    artisan
    -0.68
     Fully
    -0.68
    cham
    -0.64
    obar
    -0.63
     START
    -0.60
    yn
    -0.59
    oat
    -0.59
    neau
    -0.58
    ilde
    -0.57
    POSITIVE LOGITS
     periods
    1.28
     period
    0.91
     duration
    0.91
     continu
    0.90
     stretches
    0.89
    duration
    0.82
    period
    0.82
    term
    0.80
     eternity
    0.78
    lasting
    0.77
    Activations Density 0.078%

    No Known Activations