© 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. 6-RES-JB
    11. 1482
    Prev
    Next
    INDEX
    Explanations

    phrases indicating different approaches or methods of doing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate methods or approaches to achieve goals

    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
    ĸļ
    -0.94
    usters
    -0.83
    rake
    -0.72
    omore
    -0.70
     Tanz
    -0.69
    asts
    -0.67
    mare
    -0.66
    owship
    -0.63
    ulner
    -0.62
    ocument
    -0.60
    POSITIVE LOGITS
    finding
    0.86
    point
    0.79
    ward
    0.68
    finder
    0.67
    way
    0.66
    sey
    0.66
    fare
    0.63
    esa
    0.62
    forward
    0.60
    stop
    0.60
    Activations Density 0.023%

    No Known Activations