© 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 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. 4-RES-JB
    11. 4907
    Prev
    Next
    INDEX
    Explanations

    selections or choices being made from a group of options

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "selected"

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

    No Comments

    Negative Logits
    loo
    -0.77
    plane
    -0.72
    Net
    -0.69
    alone
    -0.66
    pir
    -0.64
     paw
    -0.63
    cer
    -0.62
    cow
    -0.62
    threat
    -0.61
    ga
    -0.61
    POSITIVE LOGITS
    selection
    0.83
    dinand
    0.81
    picked
    0.81
     Selection
    0.78
     randomly
    0.77
     selections
    0.77
    avorite
    0.74
    lime
    0.73
     "$:/
    0.72
     selected
    0.71
    Activations Density 0.033%

    No Known Activations