© 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. 7-RES-JB
    11. 22718
    Prev
    Next
    INDEX
    Explanations

    phrases related to writing or documenting information

    oai_token-act-pair · gpt-3.5-turbo

    references to notebooks and various types of shotguns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otle
    -1.00
    rations
    -0.89
    gio
    -0.85
    relation
    -0.83
    abad
    -0.81
    ration
    -0.80
    rates
    -0.79
    aton
    -0.79
    raved
    -0.78
    rate
    -0.78
    POSITIVE LOGITS
    erness
    0.76
    itton
    0.75
    halla
    0.67
    é¾įå¥ij士
    0.66
    BLE
    0.65
    lihood
    0.64
    hed
    0.64
     STOR
    0.64
    è¦ļéĨĴ
    0.62
    ï¸
    0.62
    Activations Density 0.107%

    No Known Activations