© 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. 9154
    Prev
    Next
    INDEX
    Explanations

    phrases related to obeying instructions or guidelines

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "to" indicating direction or purpose

    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
    rief
    -0.74
    rieve
    -0.70
     appealed
    -0.69
     mailed
    -0.68
    aukee
    -0.67
    ruce
    -0.67
    iba
    -0.66
    quartered
    -0.66
    ulence
    -0.65
    rieved
    -0.65
    POSITIVE LOGITS
     directions
    0.74
     tradition
    0.72
    Ô
    0.70
     Tradition
    0.70
     scripture
    0.67
    Lenin
    0.66
     varying
    0.65
     Wikipedia
    0.63
     standards
    0.63
     DSM
    0.62
    Activations Density 0.071%

    No Known Activations