© 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. 3-RES-JB
    11. 3319
    Prev
    Next
    INDEX
    Explanations

    moments or instances in a narrative

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "moment."

    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
    emale
    -0.77
    tti
    -0.74
    uct
    -0.71
     Springer
    -0.71
    LCS
    -0.70
    CHQ
    -0.69
    ply
    -0.68
    ä¸Ĭ
    -0.67
    Steel
    -0.66
    GH
    -0.65
    POSITIVE LOGITS
    aneously
    1.14
    ary
    1.06
    aries
    0.97
     moment
    0.94
    ously
    0.89
    ous
    0.88
     moments
    0.86
     gratification
    0.86
    icity
    0.81
     Moment
    0.79
    Activations Density 0.022%

    No Known Activations