© 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. 9213
    Prev
    Next
    INDEX
    Explanations

    phrases related to creating or designing something

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "the" followed by varying numeric values or ordinal indicators

    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
    govtrack
    -0.76
    ingly
    -0.67
    ANCE
    -0.66
    worn
    -0.66
    iev
    -0.66
     held
    -0.66
    played
    -0.65
    fulness
    -0.63
    Joined
    -0.62
    fully
    -0.61
    POSITIVE LOGITS
    ses
    1.06
     groundwork
    1.04
     requisite
    1.04
     entire
    0.97
     entirety
    0.96
     beginnings
    0.92
     newest
    0.91
     largest
    0.90
     latest
    0.87
     strongest
    0.86
    Activations Density 0.292%

    No Known Activations