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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 6375
    Prev
    Next
    INDEX
    Explanations

    mentions of legal verdicts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Heritage
    -0.76
    cession
    -0.71
    ohyd
    -0.68
    abb
    -0.66
    olen
    -0.66
    access
    -0.66
    cling
    -0.66
     Dak
    -0.66
    ARA
    -0.65
     Adventures
    -0.65
    POSITIVE LOGITS
     verdict
    1.22
    ysis
    0.95
    naire
    0.89
     judgement
    0.87
     judgment
    0.83
     Judgment
    0.76
    iciary
    0.76
     debtor
    0.74
    iseum
    0.72
    INAL
    0.71
    Activations Density 0.008%

    No Known Activations