© 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. 0-RES-JB
    11. 4914
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to constructing or building

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "construct" and its variations, indicating a focus on the creation or building of concepts, structures, or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scotia
    -0.76
     Thro
    -0.74
     NK
    -0.67
    shots
    -0.67
    taboola
    -0.66
    oda
    -0.65
    iere
    -0.65
     Led
    -0.63
    neck
    -0.62
    undown
    -0.62
    POSITIVE LOGITS
     construct
    3.79
     constructs
    2.56
     Construct
    2.28
    construct
    2.16
    Construct
    2.05
     constructing
    1.79
     constructor
    1.78
     constructed
    1.64
     construction
    1.48
     destruct
    1.21
    Activations Density 0.014%

    No Known Activations