© 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. 10336
    Prev
    Next
    INDEX
    Explanations

    titles or names of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and organizations

    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
    âķIJâķIJ
    -0.71
    ãĤ¤ãĥĪ
    -0.68
    piring
    -0.66
    worldly
    -0.66
    «ĺ
    -0.65
     dstg
    -0.65
    ¼
    -0.64
    bm
    -0.63
    ×ŀ
    -0.63
    vm
    -0.63
    POSITIVE LOGITS
     also
    1.52
     additionally
    1.24
     furthermore
    1.18
     retains
    1.02
     differs
    1.01
     moreover
    1.01
     emphasizes
    1.01
     therefore
    0.99
     relies
    0.99
     maintains
    0.96
    Activations Density 0.339%

    No Known Activations