© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 15405
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal claims or accusations

    oai_token-act-pair · gpt-3.5-turbo

    the term "alleges" and its variations related to accusations or claims in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     static
    -0.73
     Optim
    -0.64
     RIP
    -0.63
     prag
    -0.63
    reen
    -0.63
     Atlas
    -0.62
     Babel
    -0.62
     Cho
    -0.62
     intro
    -0.61
     ner
    -0.61
    POSITIVE LOGITS
     alleges
    3.09
     allege
    2.91
     alleging
    2.55
     alleged
    1.89
     accuses
    1.84
     allegation
    1.77
     accuse
    1.65
     allegations
    1.63
     accusing
    1.54
     accused
    1.47
    Activations Density 0.020%

    No Known Activations