© 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. 1-RES-JB
    11. 9590
    Prev
    Next
    INDEX
    Explanations

    terms related to law and policy reforms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of reforms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dak
    -0.69
    WAYS
    -0.68
     Peninsula
    -0.64
     McA
    -0.64
    CTV
    -0.63
     LIMITED
    -0.63
     Delta
    -0.62
    LAN
    -0.62
     Dominion
    -0.60
    McC
    -0.60
    POSITIVE LOGITS
     reforms
    1.12
     reform
    0.98
     decriminal
    0.88
    atile
    0.86
     overhaul
    0.82
    ĸļ
    0.81
    avorite
    0.79
    atism
    0.79
    undown
    0.78
    eatures
    0.76
    Activations Density 0.008%

    No Known Activations