© 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. 9-RES-JB
    11. 19530
    Prev
    Next
    INDEX
    Explanations

    legal and political terms related to laws and regulations

    oai_token-act-pair · gpt-3.5-turbo

    discussions about legal rights and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !.
    -1.01
    .:
    -0.86
    +.
    -0.85
    ';
    -0.82
    .;
    -0.81
    *.
    -0.81
    `.
    -0.80
    %.
    -0.78
    .",
    -0.78
    '.
    -0.77
    POSITIVE LOGITS
     outweigh
    0.58
    pires
    0.54
     harms
    0.53
     constitutes
    0.52
    ihadi
    0.52
     violates
    0.51
     entails
    0.50
     immutable
    0.48
     disliked
    0.48
    estern
    0.48
    Activations Density 1.606%

    No Known Activations