© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6702
    Prev
    Next
    INDEX
    Explanations

    references to the act of imagining or envisioning hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Imagine" signifying a hypothetical or creative scenario

    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
     territorial
    -0.65
     progress
    -0.64
     strict
    -0.64
     disposition
    -0.64
     specific
    -0.63
     marked
    -0.63
    reg
    -0.62
     dispos
    -0.61
     ref
    -0.61
     supers
    -0.60
    POSITIVE LOGITS
     Imagine
    3.40
    Imagine
    3.31
     Suppose
    1.87
     imagine
    1.80
    agine
    1.65
    Think
    1.57
     Think
    1.47
     imagining
    1.26
    Consider
    1.26
     Consider
    1.19
    Activations Density 0.016%

    No Known Activations