© 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. 2-RES-JB
    11. 21459
    Prev
    Next
    INDEX
    Explanations

    Phrases indicating editorial work or mentions of specific locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "Ed," indicating references to editorial content or individuals named Ed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [&
    -0.75
    ãģ¦
    -0.74
    falls
    -0.70
    fall
    -0.68
    ãĥĩãĤ£
    -0.67
     Scholar
    -0.66
    EStreamFrame
    -0.65
    MENTS
    -0.65
    framework
    -0.64
    è¦ļéĨĴ
    -0.64
    POSITIVE LOGITS
    monton
    1.25
    mund
    1.20
    inburgh
    1.17
    ison
    1.06
    ition
    1.03
    ifice
    0.93
    itions
    0.89
    ternity
    0.87
    psey
    0.87
    itors
    0.86
    Activations Density 0.009%

    No Known Activations