© 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. 20088
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'look' in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "look."

    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
    onds
    -0.65
    forced
    -0.63
     Unknown
    -0.63
    na
    -0.62
    mitting
    -0.61
     Recorded
    -0.60
    quished
    -0.58
    mits
    -0.57
    î
    -0.57
     constitu
    -0.56
    POSITIVE LOGITS
     look
    3.40
    look
    2.31
     Look
    2.22
     LOOK
    2.18
     looks
    2.08
    Look
    1.95
     glance
    1.94
     looked
    1.83
     stare
    1.60
     peek
    1.57
    Activations Density 0.034%

    No Known Activations