© 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. 11-RES-JB
    11. 5588
    Prev
    Next
    INDEX
    Explanations

    words related to actions or interactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "to" followed by action-oriented verbs or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Died
    -0.71
    houses
    -0.71
    slave
    -0.70
    ICLE
    -0.69
     Photography
    -0.68
    trained
    -0.68
     Mayhem
    -0.67
    HD
    -0.66
     Created
    -0.66
    Offline
    -0.66
    POSITIVE LOGITS
     reassure
    1.48
     clarify
    1.47
     reiterate
    1.39
     emphasize
    1.35
     criticize
    1.34
     underscore
    1.28
     soften
    1.28
     denounce
    1.25
     refute
    1.24
     defend
    1.22
    Activations Density 0.287%

    No Known Activations