© 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. 1067
    Prev
    Next
    INDEX
    Explanations

    phrases related to detailed discussions or debates

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "discussion" and its variations

    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
    peria
    -0.88
    closure
    -0.70
    prints
    -0.69
    clad
    -0.68
    uilt
    -0.66
    fits
    -0.66
     robber
    -0.64
    inker
    -0.63
    blem
    -0.63
    fitting
    -0.63
    POSITIVE LOGITS
     forum
    0.90
     forums
    0.88
    atorium
    0.85
     discussion
    0.82
     topics
    0.78
     boards
    0.78
    naire
    0.77
    halla
    0.74
     moderators
    0.74
    IUM
    0.72
    Activations Density 0.035%

    No Known Activations