© 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. 6-RES-JB
    11. 3052
    Prev
    Next
    INDEX
    Explanations

    instances where something or someone is considered superior or exempt from rules or standards

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "above" followed by a number

    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
    Introduced
    -0.74
     Instruments
    -0.67
    DAY
    -0.67
    dll
    -0.66
    rol
    -0.65
    Access
    -0.64
    ãĤ¹ãĥĪ
    -0.63
    Express
    -0.63
    20439
    -0.63
    Mail
    -0.63
    POSITIVE LOGITS
    ground
    1.03
    perty
    0.97
    mentioned
    0.80
     grade
    0.74
    yp
    0.72
    uckland
    0.71
    aucus
    0.70
     infinity
    0.69
    hand
    0.68
    lihood
    0.68
    Activations Density 0.020%

    No Known Activations