© 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. 3591
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of a "root."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "root" in various contexts

    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
    eers
    -0.96
    urches
    -0.84
    psey
    -0.84
    zsche
    -0.83
    abwe
    -0.82
     disadvant
    -0.80
    cffff
    -0.79
    vernment
    -0.78
    odies
    -0.76
    awaru
    -0.73
    POSITIVE LOGITS
     cellar
    0.85
    stock
    0.85
     Canal
    0.83
     canal
    0.83
    kit
    0.83
    beer
    0.74
    stocks
    0.73
     root
    0.73
    ptr
    0.71
     roots
    0.70
    Activations Density 0.018%

    No Known Activations