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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16432
    Prev
    Next
    INDEX
    Explanations

    keywords related to creativity and mental imagery

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of imagination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    paying
    -0.83
    ded
    -0.71
    cler
    -0.71
    upon
    -0.70
    ishops
    -0.69
    bye
    -0.67
    ients
    -0.66
    ldon
    -0.65
    onse
    -0.64
    bis
    -0.64
    POSITIVE LOGITS
     imagination
    1.20
     imag
    1.11
     imagin
    0.91
     imagining
    0.88
     Imag
    0.75
    istically
    0.72
    ufact
    0.72
     Balloon
    0.71
    umbered
    0.71
     Hots
    0.70
    Activations Density 0.009%

    No Known Activations