© 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 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. 3218
    Prev
    Next
    INDEX
    Explanations

    phrases related to the term "Grammys" and words related to grammar

    oai_token-act-pair · gpt-3.5-turbo

    references to the Grammy Awards and related terms

    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
    resses
    -0.73
    idth
    -0.71
    uckland
    -0.66
    ++++++++
    -0.65
    osterone
    -0.64
    xual
    -0.63
    imaru
    -0.63
    âķIJâķIJ
    -0.62
    orld
    -0.61
    éĹĺ
    -0.61
    POSITIVE LOGITS
    matical
    1.52
    matically
    1.43
    ophone
    1.25
    matic
    1.01
    mar
    0.96
    bling
    0.92
    ming
    0.91
    mer
    0.91
    mys
    0.90
    mage
    0.90
    Activations Density 0.056%

    No Known Activations