© 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. 4-RES-JB
    11. 7217
    Prev
    Next
    INDEX
    Explanations

    instances of the word "double"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "double" in various contexts

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

    No Comments

    Negative Logits
    ULE
    -0.88
    Interstitial
    -0.87
    utical
    -0.80
    ä½ľ
    -0.78
    CHAT
    -0.78
    idian
    -0.78
    utics
    -0.77
    */(
    -0.75
    atche
    -0.75
    akeru
    -0.75
    POSITIVE LOGITS
     digit
    0.92
     sided
    0.89
     digits
    0.87
     dipping
    0.85
    header
    0.83
    headers
    0.80
    leaf
    0.73
     negatives
    0.71
    ceptions
    0.66
     edged
    0.66
    Activations Density 0.014%

    No Known Activations