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

    Neuronpedia

    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. 8-RES-JB
    11. 7072
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "given"

    oai_token-act-pair · gpt-3.5-turbo

    situations where individuals are granted opportunities or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atoon
    -0.80
    iba
    -0.75
    Austral
    -0.62
     sear
    -0.62
    hed
    -0.62
     converge
    -0.61
     currents
    -0.61
    aware
    -0.61
    nel
    -0.60
    indu
    -0.60
    POSITIVE LOGITS
     choice
    1.23
     opportunity
    1.13
     chance
    1.04
    choice
    0.93
     permission
    0.81
     thumbs
    0.81
     option
    0.80
     gift
    0.78
     latitude
    0.77
     pretext
    0.76
    Activations Density 0.159%

    No Known Activations