© 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. 12158
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of 'everything' or 'all things'

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with the concept of control and change

    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
    few
    -0.77
    ktop
    -0.75
    many
    -0.68
    nai
    -0.67
    eph
    -0.67
     [|
    -0.66
    Reader
    -0.64
    sever
    -0.64
     widest
    -0.62
    orest
    -0.62
    POSITIVE LOGITS
     accounted
    0.92
     meticulously
    0.89
     interconnected
    0.89
     gravy
    0.88
     crammed
    0.84
     neatly
    0.82
     happening
    0.81
     kosher
    0.80
     culmin
    0.79
     except
    0.79
    Activations Density 0.199%

    No Known Activations