© 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. 2-RES-JB
    11. 15274
    Prev
    Next
    INDEX
    Explanations

    terms related to legal procedures and processes, such as "deposition" and "perjury."

    oai_token-act-pair · gpt-3.5-turbo

    words related to legal processes, specifically depositions and testimonies

    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
    ahime
    -0.83
    WA
    -0.79
    ãĤ¿
    -0.78
    aged
    -0.74
    strings
    -0.73
    bridge
    -0.73
    2020
    -0.70
    complex
    -0.69
    STEM
    -0.69
     Novel
    -0.67
    POSITIVE LOGITS
     deposition
    1.36
     depos
    1.28
     centrif
    1.00
    ividual
    0.89
     newsp
    0.85
     horizont
    0.81
    ongyang
    0.80
    perature
    0.80
     transcripts
    0.75
     irregularities
    0.74
    Activations Density 0.013%

    No Known Activations