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. 11-RES-JB
    6. 19372
    Prev
    Next
    INDEX
    Explanations

    legal and governmental entities such as specific courts and districts

    oai_token-act-pair · gpt-3.5-turbo

    references to legal actions and court cases

    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
    natureconservancy
    -0.81
    letes
    -0.72
     hikers
    -0.69
     Logo
    -0.64
     sacrific
    -0.64
     runners
    -0.62
     volunteers
    -0.61
     skelet
    -0.61
     astronauts
    -0.60
     binge
    -0.59
    POSITIVE LOGITS
     court
    1.35
     Court
    1.34
     Superior
    1.34
     courtroom
    1.33
     Circuit
    1.28
     courthouse
    1.24
     courts
    1.21
     Courts
    1.16
    Court
    1.10
     COURT
    1.07
    Activations Density 0.177%

    No Known Activations