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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 15726
    Prev
    Next
    INDEX
    Explanations

    references to events or instances where something is physically opened

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "opened."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subsistence
    -0.70
    eto
    -0.61
    behavior
    -0.60
    ILY
    -0.60
     attribution
    -0.58
     pund
    -0.58
    eter
    -0.57
     extremes
    -0.57
    Clock
    -0.56
     ransom
    -0.56
    POSITIVE LOGITS
     opened
    3.44
    opened
    2.47
     reopened
    2.29
     opens
    2.11
     closed
    1.75
     opening
    1.72
     open
    1.67
     reopen
    1.56
     OPEN
    1.56
    opens
    1.55
    Activations Density 0.021%

    No Known Activations