© 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. 9950
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "se" with a predominantly high activation value

    oai_token-act-pair · gpt-3.5-turbo

    variations of the prefix "se," often associated with various meanings and contexts

    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
     hoops
    -0.70
     owl
    -0.69
     shorth
    -0.69
    è¦ļéĨĴ
    -0.68
    uracy
    -0.64
     wildfire
    -0.64
     realism
    -0.63
    INGTON
    -0.63
     banter
    -0.61
    aceous
    -0.60
    POSITIVE LOGITS
    eker
    1.25
    venth
    1.22
    gments
    1.17
    vered
    1.05
    pt
    1.05
    ve
    1.02
    asons
    1.00
    xt
    0.99
    vel
    0.99
    vent
    0.99
    Activations Density 0.016%

    No Known Activations