© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1864
    Prev
    Next
    INDEX
    Explanations

    numeric values, specifically street addresses, and quantities related to metrics

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to measurements or statistics

    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
    robe
    -0.85
    book
    -0.78
    BOOK
    -0.77
    warts
    -0.76
    oms
    -0.69
    aken
    -0.68
    akable
    -0.67
    akes
    -0.66
    shake
    -0.66
    stal
    -0.65
    POSITIVE LOGITS
    mph
    1.02
    Hz
    0.99
    00000
    0.94
    âĸĪ
    0.87
     ILCS
    0.85
     mph
    0.81
    MHz
    0.79
     Hz
    0.77
    px
    0.77
     MHz
    0.77
    Activations Density 0.038%

    No Known Activations