© 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. 9-RES-JB
    11. 20750
    Prev
    Next
    INDEX
    Explanations

    phrases related to anticipation and eagerness

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to future expectations and plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.56
    oof
    -0.54
    @#&
    -0.52
    yrics
    -0.51
    didn
    -0.51
    ixty
    -0.50
    contained
    -0.49
    iuses
    -0.48
     incorrectly
    -0.48
    ¿½
    -0.47
    POSITIVE LOGITS
     tomorrow
    1.43
     someday
    1.33
     next
    1.23
     future
    1.21
     hereafter
    1.14
    morrow
    1.07
     soon
    1.06
     upcoming
    1.04
     2019
    1.01
     2020
    0.98
    Activations Density 1.753%

    No Known Activations