© 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. 9578
    Prev
    Next
    INDEX
    Explanations

    phrases that involve a comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a minimum or comparative evaluation

    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
    iard
    -0.83
    banks
    -0.77
    bending
    -0.77
    ursday
    -0.77
    ament
    -0.73
    igers
    -0.72
    bank
    -0.71
    alien
    -0.68
    rieg
    -0.65
    iets
    -0.65
    POSITIVE LOGITS
     Marketable
    0.88
    acle
    0.79
     proximity
    0.69
     acquies
    0.68
    acles
    0.68
     pretend
    0.68
     guessed
    0.66
    etheless
    0.66
     outright
    0.65
     equivalent
    0.64
    Activations Density 0.052%

    No Known Activations