© 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. 2-RES-JB
    11. 12459
    Prev
    Next
    INDEX
    Explanations

    instances where someone or something is chosen or picked for a role or position

    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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cre
    -0.68
     heels
    -0.68
    hur
    -0.67
    Net
    -0.67
    Jam
    -0.67
    ctrl
    -0.66
     sink
    -0.65
    olic
    -0.65
    pl
    -0.63
    plug
    -0.62
    POSITIVE LOGITS
     selections
    0.93
    selection
    0.91
     selected
    0.88
    selected
    0.86
     randomly
    0.86
     selection
    0.84
    ecided
    0.83
     selects
    0.82
    dinand
    0.81
     Selection
    0.79
    Activations Density 0.013%

    No Known Activations