© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11564
    Prev
    Next
    INDEX
    Explanations

    references to legal terminologies related to justice and fair treatment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of due process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sat
    -0.69
     Seymour
    -0.69
     Offline
    -0.68
     Hots
    -0.68
    adia
    -0.65
     Sheep
    -0.64
     Sek
    -0.63
    anon
    -0.62
     Wolfgang
    -0.61
     flo
    -0.61
    POSITIVE LOGITS
     diligence
    1.47
    lling
    1.12
     dilig
    0.90
    giving
    0.90
    lled
    0.88
     process
    0.85
    process
    0.83
     notice
    0.83
     respect
    0.81
     allowance
    0.81
    Activations Density 0.028%

    No Known Activations