© 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. 22637
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases ending with a period or full stop

    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
     unpredict
    -0.70
     rainbow
    -0.70
     extingu
    -0.69
     undet
    -0.68
     trivial
    -0.68
     corrid
    -0.67
     fleeting
    -0.67
     intangible
    -0.67
     plateau
    -0.67
     unsustainable
    -0.66
    POSITIVE LOGITS
     Their
    1.11
     Likewise
    1.09
     Similarly
    1.09
     Others
    1.09
     Together
    1.06
     His
    1.04
     Presumably
    1.01
     Interestingly
    0.99
     They
    0.98
     Younger
    0.98
    Activations Density 0.848%

    No Known Activations