© 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. 5072
    Prev
    Next
    INDEX
    Explanations

    phrases expressing critique or strong opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of being "out."

    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
    sembly
    -0.88
     GOODMAN
    -0.74
    odies
    -0.66
     Users
    -0.63
     Emin
    -0.63
     Funds
    -0.63
    aders
    -0.62
     colleg
    -0.61
     Yard
    -0.60
    plings
    -0.59
    POSITIVE LOGITS
    edly
    0.73
     rejection
    0.71
    stand
    0.68
    Repe
    0.68
    lined
    0.67
     lie
    0.66
    Ign
    0.65
    Latin
    0.65
    Country
    0.64
    butt
    0.63
    Activations Density 0.076%

    No Known Activations