© 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. 6-RES-JB
    11. 13568
    Prev
    Next
    INDEX
    Explanations

    the word 'opt' and its variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "opt" and its variations, indicating choices or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INESS
    -0.72
     Danger
    -0.71
    flies
    -0.71
    nces
    -0.68
    borough
    -0.65
     Famous
    -0.63
    riage
    -0.63
     Granger
    -0.61
    bred
    -0.59
     Bam
    -0.59
    POSITIVE LOGITS
     opt
    1.01
    atory
    0.90
     opting
    0.87
    uary
    0.86
     opted
    0.86
    imum
    0.84
    aye
    0.84
    atis
    0.83
    nir
    0.83
    ates
    0.77
    Activations Density 0.011%

    No Known Activations