© 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. 501
    Prev
    Next
    INDEX
    Explanations

    Latin words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to classification and taxonomy in language

    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
     sustainability
    -0.75
    Timer
    -0.73
    timer
    -0.72
    abytes
    -0.70
    timeout
    -0.69
    insured
    -0.68
    ertodd
    -0.67
     accountability
    -0.67
     Blair
    -0.66
    vidia
    -0.66
    POSITIVE LOGITS
    ËĪ
    1.19
    tymology
    1.14
     pronunciation
    1.03
     pron
    1.02
    É
    1.01
     noun
    0.97
     plural
    0.95
     suffix
    0.92
     vowel
    0.91
     conson
    0.91
    Activations Density 0.382%

    No Known Activations