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. 8-RES-JB
    6. 16385
    Prev
    Next
    INDEX
    Explanations

    time-related phrases or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a duration or a state of continuity until a specified event occurs

    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
    è¦ļéĨĴ
    -0.73
     Actions
    -0.67
     guiName
    -0.67
    groupon
    -0.63
    ãĥ´
    -0.63
     EntityItem
    -0.62
    ãĥĦ
    -0.62
     Blueprint
    -0.61
    \\\\\\\\
    -0.61
     Holding
    -0.60
    POSITIVE LOGITS
    helm
    0.73
    maxwell
    0.72
     intervened
    0.67
     exhaustion
    0.67
     expires
    0.66
     reinforcements
    0.66
     reaches
    0.64
    iless
    0.64
    izons
    0.63
     finally
    0.63
    Activations Density 0.160%

    No Known Activations