© 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. 9-RES-JB
    6. 13419
    Prev
    Next
    INDEX
    Explanations

    locations or legal terms

    oai_token-act-pair · gpt-3.5-turbo

    legal terms and references to court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     loads
    -0.68
    natureconservancy
    -0.66
    etus
    -0.64
     flashes
    -0.64
     vitamins
    -0.64
     fans
    -0.62
     astronauts
    -0.62
    letes
    -0.62
     linem
    -0.61
     charism
    -0.61
    POSITIVE LOGITS
     courtroom
    1.17
     Circuit
    1.08
     court
    1.07
     courts
    1.06
     Court
    1.05
     Courts
    1.01
    trial
    0.98
     Superior
    0.93
     courthouse
    0.92
     COURT
    0.92
    Activations Density 0.220%

    No Known Activations