© 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. 6-RES-JB
    11. 14564
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning legal actions or court cases

    oai_token-act-pair · gpt-3.5-turbo

    references to plaintiffs in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apes
    -0.76
     [|
    -0.74
    ahime
    -0.74
    apo
    -0.73
    OVA
    -0.70
    inventoryQuantity
    -0.70
    lasses
    -0.69
    ollo
    -0.68
    canon
    -0.66
    adden
    -0.64
    POSITIVE LOGITS
    iffs
    0.94
     plaintiffs
    0.94
     plaintiff
    0.85
     suing
    0.84
     attorneys
    0.76
     alleges
    0.75
     sued
    0.75
     defendants
    0.71
     Plaint
    0.70
     briefs
    0.70
    Activations Density 0.025%

    No Known Activations