© 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. 11-RES-JB
    11. 20746
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "freedom," especially in the context of free markets and speech

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "free" in various contexts, particularly related to markets and speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sidx
    -0.72
     Redux
    -0.69
    older
    -0.69
     Shack
    -0.68
     Takeru
    -0.68
    URRENT
    -0.65
    ettings
    -0.64
    ITED
    -0.63
     Glac
    -0.63
    warts
    -0.61
    POSITIVE LOGITS
     speech
    1.06
    zing
    1.03
    zers
    1.03
    bies
    0.99
     enterprise
    0.95
    boot
    0.94
    fall
    0.93
    bie
    0.89
     spirited
    0.88
     roam
    0.87
    Activations Density 0.035%

    No Known Activations