© 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. 10730
    Prev
    Next
    INDEX
    Explanations

    numerical values related to addresses, measurements, and quantities

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values, particularly related to street addresses or quantities

    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
    phrine
    -0.84
    actic
    -0.79
    omial
    -0.76
    gotten
    -0.75
    atics
    -0.74
    scene
    -0.74
    ogue
    -0.73
     Laden
    -0.73
    ces
    -0.73
    ufact
    -0.72
    POSITIVE LOGITS
    Hz
    0.80
    wcsstore
    0.79
    é¾įå¥ij士
    0.77
    yne
    0.77
    ansas
    0.76
    hz
    0.72
    IELD
    0.69
     msec
    0.68
     crore
    0.68
    Apps
    0.66
    Activations Density 0.029%

    No Known Activations