© 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. 6-RES-JB
    11. 3084
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating varying degrees of seriousness or complexity

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing varying degrees of intensity or seriousness

    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
    SEA
    -0.80
    essler
    -0.72
    OVER
    -0.71
    FORE
    -0.70
    Hide
    -0.68
     Drawn
    -0.68
    along
    -0.66
     Contains
    -0.65
    owell
    -0.64
    Unique
    -0.63
    POSITIVE LOGITS
     than
    1.49
    than
    1.14
     versions
    1.08
     Than
    1.06
     forms
    1.03
     sounding
    1.00
     alternatives
    0.96
     pursuits
    0.93
     ones
    0.92
     formulations
    0.86
    Activations Density 0.144%

    No Known Activations