© 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. 11222
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to news articles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "the" in various contexts, particularly emphasizing its frequency and use in conjunction with other content

    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
    ãĥĺ
    -0.80
    heit
    -0.71
    rade
    -0.69
    strate
    -0.68
    #$
    -0.67
    factor
    -0.66
    Tier
    -0.65
    entimes
    -0.64
    )=(
    -0.63
    Detect
    -0.62
    POSITIVE LOGITS
     full
    1.34
     entire
    1.31
     latest
    1.25
     rest
    1.22
     entirety
    1.19
     whole
    1.16
     remainder
    1.10
     slideshow
    1.07
     FULL
    1.04
     original
    1.03
    Activations Density 0.101%

    No Known Activations