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. 593
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific periods of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to durations of time spent in various contexts or roles

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.77
    redict
    -0.68
    yout
    -0.66
    imeter
    -0.64
    eware
    -0.62
     somet
    -0.62
    ythm
    -0.60
     Causes
    -0.59
     Yose
    -0.59
    ãĥª
    -0.59
    POSITIVE LOGITS
     abroad
    1.09
     aboard
    0.96
     overseas
    0.94
     atop
    0.89
     coaching
    0.88
     stint
    0.86
     photograp
    0.82
     studying
    0.79
     captivity
    0.78
     spent
    0.77
    Activations Density 0.196%

    No Known Activations