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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3504
    Prev
    Next
    INDEX
    Explanations

    instances of the word "weigh" and related variations, displaying a focus on evaluating options or opinions

    oai_token-act-pair · gpt-3.5-turbo

    references to weighing decisions or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĨãĤ£
    -0.79
    nered
    -0.78
    algia
    -0.75
    heid
    -0.73
    anie
    -0.66
     Kart
    -0.65
    asma
    -0.65
     Parables
    -0.64
    LES
    -0.64
    chief
    -0.62
    POSITIVE LOGITS
     weigh
    1.09
     weighing
    0.87
     heaviest
    0.84
     weighed
    0.83
     probabilities
    0.79
     heavily
    0.79
     weights
    0.78
     judgement
    0.78
     pros
    0.76
     advis
    0.73
    Activations Density 0.044%

    No Known Activations