© 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. 3-RES-JB
    11. 13125
    Prev
    Next
    INDEX
    Explanations

    the word "decision"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "decision."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingers
    -0.79
    amina
    -0.72
     additive
    -0.71
    hern
    -0.68
    ubric
    -0.67
    orsi
    -0.67
    hemat
    -0.67
    vae
    -0.66
    izont
    -0.66
    atomic
    -0.65
    POSITIVE LOGITS
     makers
    0.93
     decisions
    0.92
     decision
    0.91
     maker
    0.75
     stance
    0.71
     regarding
    0.70
     ACTIONS
    0.70
    making
    0.69
     calculus
    0.68
     decided
    0.67
    Activations Density 0.033%

    No Known Activations