© 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. 10-RES-JB
    6. 6542
    Prev
    Next
    INDEX
    Explanations

    words related to cover-ups and concealment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "cover-up."

    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
     diam
    -0.71
     Confederation
    -0.69
     AAA
    -0.67
     Bucc
    -0.67
     constitu
    -0.66
     supreme
    -0.64
     acknowled
    -0.61
     Fi
    -0.61
     elector
    -0.61
     Universal
    -0.60
    POSITIVE LOGITS
    your
    1.18
    sheet
    1.09
    up
    1.07
    camp
    1.06
    around
    1.03
    topic
    1.02
    picking
    0.99
    resistant
    0.99
    mining
    0.99
    job
    0.98
    Activations Density 0.089%

    No Known Activations