© 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. 9-RES-JB
    11. 16058
    Prev
    Next
    INDEX
    Explanations

    measures of quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a measured quantity or amount

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.94
    ħĭ
    -0.91
     Cosponsors
    -0.83
    most
    -0.82
    Ń·
    -0.79
    few
    -0.77
    \\\\\\\\
    -0.75
    paces
    -0.75
    iors
    -0.74
    inks
    -0.72
    POSITIVE LOGITS
     money
    1.12
     time
    0.98
     information
    0.96
     firepower
    0.96
     detail
    0.94
     material
    0.93
     variance
    0.92
     effort
    0.92
     manpower
    0.89
     attention
    0.88
    Activations Density 0.086%

    No Known Activations