© 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. 20696
    Prev
    Next
    INDEX
    Explanations

    sentence transitions or segues

    oai_token-act-pair · gpt-3.5-turbo

    instances of conversational interjections or transitional phrases

    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
    âĹ¼
    -0.69
    è¦ļéĨĴ
    -0.63
    MX
    -0.63
    illary
    -0.62
    igraph
    -0.61
     Parables
    -0.60
     flair
    -0.60
     tab
    -0.59
     booth
    -0.59
     vain
    -0.58
    POSITIVE LOGITS
    esley
    1.03
    come
    0.96
    ington
    0.88
    espie
    0.77
    spring
    0.70
    ards
    0.70
    adays
    0.69
    INGTON
    0.68
    Coin
    0.68
    FTWARE
    0.68
    Activations Density 0.026%

    No Known Activations