Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 91
    Prev
    Next
    INDEX
    Explanations

    the word "imagine" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "imagine."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "imagine" in various contexts

    oai_token-act-pair · gpt-4-turbo
    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
    ixt
    -0.72
    inals
    -0.71
    bard
    -0.71
    Methods
    -0.71
    inance
    -0.70
    church
    -0.70
    matter
    -0.68
    wa
    -0.68
    iding
    -0.67
    meta
    -0.67
    POSITIVE LOGITS
     imagine
    0.98
    lihood
    0.93
     imagining
    0.80
     msec
    0.76
     Imagine
    0.75
     hypot
    0.75
     aloud
    0.74
    ĸļ
    0.73
     Ily
    0.69
    orial
    0.69
    Activations Density 0.016%

    No Known Activations