© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 11133
    Prev
    Next
    INDEX
    Explanations

    time-related expressions and phases

    oai_token-act-pair · gpt-3.5-turbo

    the word "While" followed by various phrases indicating ongoing situations or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isable
    -0.84
    ISE
    -0.77
    omet
    -0.76
    urable
    -0.71
    aer
    -0.70
    ise
    -0.69
    enter
    -0.66
    elled
    -0.66
    ding
    -0.66
    iotic
    -0.66
    POSITIVE LOGITS
     acknowledging
    0.88
     browsing
    0.85
     researching
    0.84
     attending
    0.83
     discussing
    0.79
     touring
    0.79
     conced
    0.77
     commenting
    0.76
     agreeing
    0.75
     compiling
    0.74
    Activations Density 0.041%

    No Known Activations