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. 10037
    Prev
    Next
    INDEX
    Explanations

    keyword "During" indicating a specific time period

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "During" indicating events or activities occurring at a specific time

    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
    ettle
    -0.73
    NRS
    -0.72
    optional
    -0.71
    tools
    -0.70
    ould
    -0.65
    76561
    -0.65
    tan
    -0.64
    straight
    -0.63
    md
    -0.62
    ele
    -0.62
    POSITIVE LOGITS
    itialized
    0.89
     periods
    0.78
    ventory
    0.75
     emergencies
    0.72
     halftime
    0.69
     renovations
    0.67
     wartime
    0.67
     interviews
    0.66
     daylight
    0.66
     times
    0.66
    Activations Density 0.028%

    No Known Activations