© 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. 7-RES-JB
    11. 7890
    Prev
    Next
    INDEX
    Explanations

    Phrases related to imagining or envisioning scenarios

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing the act of imagining or envisioning scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bard
    -0.90
    die
    -0.79
    anski
    -0.75
    hide
    -0.73
    elight
    -0.72
    woods
    -0.71
    unker
    -0.69
    ged
    -0.69
    idelines
    -0.66
    wood
    -0.65
    POSITIVE LOGITS
     how
    0.85
    lihood
    0.83
     why
    0.75
     scenarios
    0.74
     what
    0.73
     encountering
    0.72
     ourselves
    0.71
     someday
    0.70
     imagine
    0.68
     waking
    0.67
    Activations Density 0.036%

    No Known Activations