© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 22295
    Prev
    Next
    INDEX
    Explanations

    mentions of specific terms related to laws and regulations, especially focusing on existing conditions and eminent issues

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to medical conditions and legal issues

    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
    igans
    -0.78
    onew
    -0.75
    apo
    -0.74
    Crunch
    -0.71
    ier
    -0.71
    ère
    -0.70
    neau
    -0.70
    alist
    -0.70
    ahime
    -0.68
    arily
    -0.68
    POSITIVE LOGITS
    ãĥŁ
    0.84
     circumstances
    0.82
     Persons
    0.80
    lihood
    0.80
     substances
    0.78
    ãĥ³
    0.76
     persons
    0.75
     Diseases
    0.69
     substance
    0.68
    ãĥĥãĥī
    0.68
    Activations Density 0.176%

    No Known Activations