© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 13459
    Prev
    Next
    INDEX
    Explanations

    the word "mock" and variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to "mock" and its variations, indicating a focus on satirical or imitative themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cryst
    -0.82
     Horizon
    -0.75
    metic
    -0.71
     arrang
    -0.69
    edin
    -0.68
     compan
    -0.68
    omen
    -0.65
    ettel
    -0.64
     violet
    -0.63
    OA
    -0.63
    POSITIVE LOGITS
     Mock
    1.12
    ument
    0.92
    eries
    0.89
     mock
    0.88
    ito
    0.83
    ety
    0.80
    atory
    0.79
    eting
    0.78
     mocking
    0.77
    ery
    0.76
    Activations Density 0.030%

    No Known Activations