© 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. 19670
    Prev
    Next
    INDEX
    Explanations

    legal or financial settlements

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or financial settlements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    inx
    -0.97
    enic
    -0.92
    cemic
    -0.87
    asus
    -0.83
    Ĭ±
    -0.80
    ordon
    -0.76
    ussen
    -0.76
    oppy
    -0.74
    emis
    -0.74
    erva
    -0.73
    POSITIVE LOGITS
     settlement
    1.38
     settlements
    1.22
     Settlement
    1.15
    ettlement
    0.95
     agreement
    0.93
     agreements
    0.89
     Sett
    0.79
    sett
    0.78
     Agreement
    0.76
     settle
    0.76
    Activations Density 0.010%

    No Known Activations