© 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. 8-RES-JB
    11. 24396
    Prev
    Next
    INDEX
    Explanations

    legal-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to educational or regulatory contexts, particularly involving legal custody and financial institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Archdemon
    -0.58
    Motor
    -0.57
    Sax
    -0.55
     sqor
    -0.54
    pedia
    -0.52
    Äĩ
    -0.52
    stown
    -0.52
    onday
    -0.51
    tm
    -0.51
    hander
    -0.50
    POSITIVE LOGITS
     holdings
    0.57
     MIA
    0.52
    anwhile
    0.52
    ortium
    0.51
    anges
    0.51
     Cohn
    0.48
    gio
    0.47
     Cox
    0.47
     trust
    0.47
     dues
    0.47
    Activations Density 1.014%

    No Known Activations