© 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. 2-RES-JB
    11. 5804
    Prev
    Next
    INDEX
    Explanations

    instances where a document mentions fractions in relation to quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to fractions and measurements of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     legitimate
    -0.69
     prohib
    -0.68
     periphery
    -0.68
     signature
    -0.67
    ocratic
    -0.65
    dyl
    -0.63
     sneaky
    -0.61
     compelling
    -0.61
     rings
    -0.61
    LAN
    -0.61
    POSITIVE LOGITS
    tenance
    1.05
    theless
    0.98
    etheless
    0.93
    foundland
    0.92
    quartered
    0.92
    geant
    0.91
    ãĥ¯ãĥ³
    0.85
    terness
    0.84
    ãĥķãĤ¡
    0.82
    forth
    0.81
    Activations Density 0.013%

    No Known Activations