© 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. 13679
    Prev
    Next
    INDEX
    Explanations

    hyphenated words with "light" in them and their related concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to light rail projects and infrastructure

    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
     prob
    -0.63
     rightful
    -0.62
    «ĺ
    -0.62
     NAFTA
    -0.61
    Ĥİ
    -0.61
     intest
    -0.61
     Mock
    -0.61
     vouchers
    -0.60
     blindly
    -0.60
     Claus
    -0.60
    POSITIVE LOGITS
    skinned
    1.25
    duty
    1.18
    touch
    1.15
    hearted
    1.10
    medium
    1.10
    filled
    1.10
    rail
    1.09
    colored
    1.08
    footed
    1.06
    bodied
    1.06
    Activations Density 0.046%

    No Known Activations