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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 18741
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and law enforcement activities, particularly involving jails and district attorneys

    oai_token-act-pair · gpt-3.5-turbo

    references to legal institutions and authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģį
    -0.77
    rawdownloadcloneembedreportprint
    -0.74
    iasm
    -0.71
     gif
    -0.66
    ersen
    -0.65
     idols
    -0.64
    itely
    -0.64
    stream
    -0.63
    iday
    -0.61
     Buddha
    -0.59
    POSITIVE LOGITS
    abulary
    0.91
     Enforcement
    0.85
     Deaths
    0.81
     Municipal
    0.76
     Militia
    0.74
     Corrections
    0.73
    uties
    0.72
     Sheriff
    0.72
     Cyrus
    0.72
     District
    0.72
    Activations Density 0.282%

    No Known Activations