© 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. 10-RES-JB
    11. 10559
    Prev
    Next
    INDEX
    Explanations

    phrases portraying a sense of totality or completion

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "all" or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.75
    hov
    -0.68
    raid
    -0.63
     Remastered
    -0.63
    Led
    -0.62
    gypt
    -0.62
    nell
    -0.62
     nowhere
    -0.61
    deck
    -0.61
    lav
    -0.60
    POSITIVE LOGITS
     traces
    1.07
    usions
    1.06
     sorts
    1.02
     semblance
    1.01
    ude
    1.00
    uding
    0.98
     kinds
    0.97
    ocating
    0.93
    udes
    0.92
     else
    0.91
    Activations Density 0.074%

    No Known Activations