© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 19956
    Prev
    Next
    INDEX
    Explanations

    legal terms such as "Court of Appeals" in the context of judicial decisions and proceedings

    oai_token-act-pair · gpt-3.5-turbo

    references to the Court of Appeals

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

    No Comments

    Negative Logits
    ku
    -0.75
    fters
    -0.70
     Horus
    -0.69
     Hussain
    -0.69
     Zi
    -0.66
    kson
    -0.66
    ifa
    -0.66
     Serpent
    -0.65
     Lann
    -0.64
     Pesh
    -0.64
    POSITIVE LOGITS
     Appeals
    1.01
     hearings
    0.99
     commissions
    0.97
     Tribunal
    0.91
    Court
    0.90
     tribunal
    0.84
     judge
    0.84
    istrate
    0.83
     judges
    0.82
     appellate
    0.82
    Activations Density 0.011%

    No Known Activations