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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 5401
    Prev
    Next
    INDEX
    Explanations

    phrases related to imagination and speculation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of the concept of imagination or the act of envisioning scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iminary
    -0.75
    elight
    -0.71
    aina
    -0.71
    tesy
    -0.69
    Trust
    -0.69
    endum
    -0.69
    ged
    -0.67
    haar
    -0.67
    estones
    -0.67
    emphasis
    -0.67
    POSITIVE LOGITS
     how
    1.15
     why
    0.99
     encountering
    0.98
     scenarios
    0.97
     needing
    0.89
     imagining
    0.88
     what
    0.88
     waking
    0.82
     scenario
    0.81
    lihood
    0.80
    Activations Density 0.050%

    No Known Activations