© 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. 23936
    Prev
    Next
    INDEX
    Explanations

    the word "few" followed by some description or entity

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating scarcity or limited availability

    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
    ICO
    -0.71
     sacrific
    -0.65
    HEAD
    -0.63
     indo
    -0.62
     Surviv
    -0.61
     destro
    -0.61
    consumer
    -0.60
     Compass
    -0.60
    Rot
    -0.60
     Kad
    -0.59
    POSITIVE LOGITS
    est
    1.15
     remaining
    1.07
     hundred
    1.03
     dozen
    0.97
     thousand
    0.87
    ieth
    0.83
     remnant
    0.82
     surviving
    0.81
     exceptions
    0.81
     exception
    0.78
    Activations Density 0.049%

    No Known Activations