© 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. 10-RES-JB
    11. 13749
    Prev
    Next
    INDEX
    Explanations

    references to legal or human rights-related terms

    oai_token-act-pair · gpt-3.5-turbo

    discussions related to civil rights and liberties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Solitaire
    -0.72
     Sark
    -0.68
    BALL
    -0.66
    asty
    -0.65
     Clover
    -0.65
     Claus
    -0.63
    annis
    -0.62
    Lens
    -0.59
     Petersen
    -0.58
    ogle
    -0.58
    POSITIVE LOGITS
     rights
    1.08
    rights
    1.06
     protections
    1.01
     holders
    0.98
     conferred
    0.97
     Rights
    0.96
     guaranteed
    0.95
     afforded
    0.93
     enshr
    0.92
     violations
    0.92
    Activations Density 0.041%

    No Known Activations