© 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 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. 3-RES-JB
    11. 10396
    Prev
    Next
    INDEX
    Explanations

    instances of the word "discussion"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of discussions on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peria
    -0.77
    ensions
    -0.75
    uilt
    -0.71
    otto
    -0.71
    prints
    -0.68
    printed
    -0.68
    otted
    -0.67
    ussy
    -0.67
    clad
    -0.66
    elled
    -0.65
    POSITIVE LOGITS
     forum
    0.97
     forums
    0.93
    ļéĨĴ
    0.91
     discussion
    0.91
    atorium
    0.81
     exchanges
    0.79
     discussions
    0.79
     topics
    0.79
    ij士
    0.78
    naire
    0.77
    Activations Density 0.020%

    No Known Activations