© 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. 2013
    Prev
    Next
    INDEX
    Explanations

    instances of the word "extract" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    the term "extract" and its variations in different contexts

    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
    ndra
    -0.70
     damned
    -0.67
    ggle
    -0.67
    ned
    -0.64
    ãĥ¥
    -0.63
    stand
    -0.62
    osuke
    -0.62
     Rear
    -0.61
    nd
    -0.60
    die
    -0.60
    POSITIVE LOGITS
    ions
    1.09
    ract
    0.94
    racted
    0.92
    ivist
    0.90
    raction
    0.90
    ngth
    0.89
    IONS
    0.86
    utic
    0.84
    ION
    0.82
    iary
    0.79
    Activations Density 0.029%

    No Known Activations