Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 22816
    Prev
    Next
    INDEX
    Explanations

    legal terms related to court orders or decisions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legislative mandates and the concept of redistricting

    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
    ubes
    -0.73
     RS
    -0.64
     FB
    -0.63
     fences
    -0.62
     row
    -0.61
     NX
    -0.59
     EX
    -0.59
     hypers
    -0.59
     FC
    -0.57
     hyper
    -0.57
    POSITIVE LOGITS
    mand
    4.75
    Mand
    2.06
     mand
    1.68
     Mand
    1.34
     mandated
    1.10
    minist
    1.08
     Mandatory
    1.06
    required
    1.02
    aband
    0.97
    mong
    0.97
    Activations Density 0.024%

    No Known Activations