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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 24566
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to legal trials

    oai_token-act-pair · gpt-3.5-turbo

    mentions of legal trials and court proceedings

    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
    olen
    -0.73
    orns
    -0.73
    ulic
    -0.69
    ula
    -0.68
    kell
    -0.66
    CRE
    -0.66
    lav
    -0.65
    oute
    -0.64
    otle
    -0.63
     ut
    -0.61
    POSITIVE LOGITS
    eering
    0.88
     hearings
    0.86
    eer
    0.85
    imony
    0.81
    neys
    0.81
     Trials
    0.77
    Court
    0.75
    naire
    0.74
     judge
    0.74
     Trial
    0.72
    Activations Density 0.012%

    No Known Activations