© 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. 0-RES-JB
    11. 15061
    Prev
    Next
    INDEX
    Explanations

    phrases related to human rights

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     simulated
    -0.66
     cycl
    -0.66
     burst
    -0.65
     tac
    -0.64
    nn
    -0.63
    ann
    -0.63
    che
    -0.63
     taco
    -0.63
     inactive
    -0.62
    inet
    -0.61
    POSITIVE LOGITS
     Rights
    3.86
    rights
    2.68
     rights
    2.62
     Liberties
    1.74
     liberties
    1.33
     freedoms
    1.32
    yrights
    1.27
     Responsibility
    1.20
    IGHTS
    1.19
     Equality
    1.13
    Activations Density 0.010%

    No Known Activations