© 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. 1-RES-JB
    11. 12921
    Prev
    Next
    INDEX
    Explanations

    verbs related to making a decision

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "decide."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resa
    -0.70
    ammers
    -0.64
     Dak
    -0.64
    acking
    -0.63
    acing
    -0.63
    riet
    -0.63
    att
    -0.62
    urdue
    -0.60
    lat
    -0.60
    outh
    -0.60
    POSITIVE LOGITS
     decide
    0.98
     decides
    0.92
    使
    0.83
     decided
    0.81
    Ļ½
    0.78
     deciding
    0.75
     Leilan
    0.74
    Ń·
    0.74
     Garc
    0.72
    Ī
    0.69
    Activations Density 0.010%

    No Known Activations