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. 4-RES-JB
    6. 23598
    Prev
    Next
    INDEX
    Explanations

    time-related phrases indicating an event or point in time

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or milestones

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

    No Comments

    Negative Logits
     Recommend
    -0.71
    dylib
    -0.68
    Topics
    -0.66
    erers
    -0.64
    ARDS
    -0.63
     Regardless
    -0.63
    .--
    -0.62
    BILITIES
    -0.62
    lime
    -0.61
     preferably
    -0.61
    POSITIVE LOGITS
     inception
    1.04
    anmar
    0.82
     initial
    0.72
    imbabwe
    0.71
     previous
    0.67
     introduction
    0.66
     estab
    0.65
     advent
    0.65
     defunct
    0.64
     christ
    0.64
    Activations Density 0.130%

    No Known Activations