© 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. 6-RES-JB
    11. 5500
    Prev
    Next
    INDEX
    Explanations

    mentions of concepts related to order and structure, such as "order in nature" or "social order"

    oai_token-act-pair · gpt-3.5-turbo

    references to concepts of order and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ©
    -0.75
    rolet
    -0.73
     Nadu
    -0.70
    vae
    -0.70
     Miliband
    -0.69
    cit
    -0.68
    burgh
    -0.67
    peria
    -0.67
    sonian
    -0.67
    lehem
    -0.64
    POSITIVE LOGITS
    lies
    1.41
    liness
    1.10
    eous
    0.88
    ylum
    0.84
    etary
    0.84
    books
    0.80
    eering
    0.75
    uria
    0.75
    able
    0.75
    ality
    0.74
    Activations Density 0.025%

    No Known Activations