© 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. 0-RES-JB
    11. 13312
    Prev
    Next
    INDEX
    Explanations

    verbs related to the process of making laws or decisions

    oai_token-act-pair · gpt-3.5-turbo

    words related to enacting laws or policies

    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
     mole
    -0.62
    fing
    -0.62
    #$
    -0.61
     pod
    -0.61
    photo
    -0.61
     Mail
    -0.60
    lv
    -0.60
    oux
    -0.59
    lich
    -0.59
     Carlo
    -0.59
    POSITIVE LOGITS
     enacted
    2.91
     enact
    2.69
     enactment
    2.10
     legisl
    1.42
     repealed
    1.42
     promulg
    1.26
     Legislation
    1.24
     instituted
    1.24
     repealing
    1.23
     statutes
    1.21
    Activations Density 0.015%

    No Known Activations