© 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. 1-RES-JB
    11. 10229
    Prev
    Next
    INDEX
    Explanations

    references to physical movements or conditions involving the legs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lim" or its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ALK
    -0.77
    EEK
    -0.76
    Kent
    -0.70
    YE
    -0.68
    Brand
    -0.64
     Watching
    -0.64
     Citizens
    -0.62
    ãĥ¯ãĥ³
    -0.62
    ATA
    -0.62
     Deadly
    -0.61
    POSITIVE LOGITS
     lim
    1.26
    elight
    1.01
    ptin
    0.94
    bered
    0.92
    inished
    0.90
    ovable
    0.89
    erick
    0.87
     corrid
    0.87
    pless
    0.86
    ewater
    0.84
    Activations Density 0.003%

    No Known Activations