© 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. 6-RES-JB
    11. 17669
    Prev
    Next
    INDEX
    Explanations

    phrases related to cost, pricing, and financial terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to levels of cost, risk, and efficiency

    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
    isters
    -0.69
    ullah
    -0.69
     Fargo
    -0.66
    inals
    -0.66
     Boris
    -0.64
     Guards
    -0.64
    thia
    -0.63
     Tayyip
    -0.63
     McGee
    -0.62
     Budd
    -0.62
    POSITIVE LOGITS
     expense
    1.04
     level
    0.98
     disadvantage
    0.91
     scale
    0.90
     behest
    0.89
     levels
    0.87
     rate
    0.85
     pace
    0.83
     LEVEL
    0.82
     speeds
    0.81
    Activations Density 0.187%

    No Known Activations