© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 12375
    Prev
    Next
    INDEX
    Explanations

    instances of the word "discussion"

    oai_token-act-pair · gpt-3.5-turbo

    references to ongoing discussions or debates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peria
    -0.78
    closure
    -0.73
    fits
    -0.71
    prints
    -0.68
    clad
    -0.67
     robber
    -0.63
    inates
    -0.62
    duc
    -0.61
    uilt
    -0.60
    photos
    -0.59
    POSITIVE LOGITS
     forum
    0.92
     forums
    0.91
     discussion
    0.88
    atorium
    0.87
     topics
    0.83
     concerning
    0.82
     topic
    0.80
     boards
    0.79
     revolves
    0.79
     discussing
    0.77
    Activations Density 0.043%

    No Known Activations