© 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. 10-RES-JB
    11. 19086
    Prev
    Next
    INDEX
    Explanations

    phrases related to freedom of speech

    oai_token-act-pair · gpt-3.5-turbo

    mentions of free speech and related legal concepts

    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
     Dani
    -0.72
    hews
    -0.70
    ocamp
    -0.67
    xon
    -0.67
     Hitch
    -0.66
    erald
    -0.65
    20439
    -0.65
     Lans
    -0.65
     Stab
    -0.64
    inka
    -0.64
    POSITIVE LOGITS
     rights
    1.12
     freedoms
    0.94
     protections
    0.94
    rights
    0.93
    speech
    0.91
     Rights
    0.89
     suppression
    0.86
     freedom
    0.82
     Yiannopoulos
    0.82
     liberties
    0.81
    Activations Density 0.042%

    No Known Activations