© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 15074
    Prev
    Next
    INDEX
    Explanations

    instances of the word "seems"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     special
    -0.57
     historic
    -0.54
    pat
    -0.53
     telephone
    -0.53
     Submit
    -0.53
    ibrary
    -0.53
     confidential
    -0.50
    stic
    -0.50
     medical
    -0.50
     comprehensive
    -0.49
    POSITIVE LOGITS
     seems
    3.03
     seemed
    2.27
     seem
    2.26
     appears
    2.24
     Seems
    1.93
     tends
    1.68
     resembles
    1.58
     feels
    1.58
     reminds
    1.56
     suggests
    1.53
    Activations Density 0.023%

    No Known Activations