© 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. 7533
    Prev
    Next
    INDEX
    Explanations

    phrases related to focusing on something for detailed observation or examination

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "Look" indicating a call to attention or action

    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
    cha
    -0.69
     sustaining
    -0.67
     pending
    -0.65
     extinguished
    -0.65
     circulating
    -0.64
     corpus
    -0.62
     attendant
    -0.62
     dying
    -0.61
     governing
    -0.60
     prevailing
    -0.60
    POSITIVE LOGITS
     Look
    3.37
    Look
    2.64
    look
    2.40
     LOOK
    2.13
     look
    2.04
     Looks
    1.83
     Looking
    1.44
     Listen
    1.41
     looks
    1.36
    Looks
    1.30
    Activations Density 0.009%

    No Known Activations