© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 13587
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names, particularly related to individuals and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     internationally
    -0.50
     prompting
    -0.46
     nationally
    -0.46
     afterward
    -0.45
     past
    -0.45
     every
    -0.44
     outside
    -0.44
     firsthand
    -0.44
     [âĢ¦]
    -0.43
     requiring
    -0.43
    POSITIVE LOGITS
    isoft
    0.65
    idae
    0.62
    TeX
    0.61
    Äĵ
    0.60
    anus
    0.59
    utenberg
    0.59
    annis
    0.59
    aceae
    0.58
    itech
    0.57
    istar
    0.57
    Activations Density 0.919%

    No Known Activations