© 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. 11-RES-JB
    6. 1675
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential advantages and disadvantages of different situations or choices

    oai_token-act-pair · gpt-3.5-turbo

    words associated with pros and cons or trade-offs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ravel
    -0.78
    ãĤ¼ãĤ¦ãĤ¹
    -0.77
    rained
    -0.74
    alde
    -0.72
    hips
    -0.67
    ocally
    -0.66
    ANN
    -0.64
    Spawn
    -0.64
    erved
    -0.63
    uild
    -0.62
    POSITIVE LOGITS
     implication
    0.91
    lihood
    0.91
     factor
    0.90
    aminer
    0.87
     downside
    0.87
     upside
    0.86
     proposition
    0.81
     effect
    0.81
     thereof
    0.80
     drawback
    0.77
    Activations Density 0.087%

    No Known Activations