© 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. 0-RES-JB
    11. 10201
    Prev
    Next
    INDEX
    Explanations

    mentions of zoos

    oai_token-act-pair · gpt-3.5-turbo

    references to zoos and their roles or contributions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constituent
    -0.73
     manifest
    -0.66
     incarn
    -0.66
    ppe
    -0.64
     inst
    -0.63
    å¼
    -0.63
     secondary
    -0.62
     basis
    -0.61
     primarily
    -0.61
     delivering
    -0.59
    POSITIVE LOGITS
    oos
    4.94
    oo
    2.23
    oons
    1.35
    oola
    1.25
    oop
    1.24
    ooo
    1.17
    ozo
    1.16
    oon
    1.16
    ois
    1.15
    zees
    1.13
    Activations Density 0.013%

    No Known Activations