© 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. 10-RES-JB
    11. 3395
    Prev
    Next
    INDEX
    Explanations

    phrases related to activities or events happening during the late night

    oai_token-act-pair · gpt-3.5-turbo

    references to late-night occurrences or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •GPT2 L10 resid: 'LRRRRRLLRRRL'[:-2]
    •GPT2 L10 resid: 'LRRRRRLLRRRL'[:-3]

    No Comments

    Negative Logits
    İĭ
    -0.95
    arte
    -0.80
    adra
    -0.78
    orthy
    -0.77
    oS
    -0.77
    è£ħ
    -0.77
    ifice
    -0.77
    urat
    -0.76
    ortium
    -0.76
    rane
    -0.76
    POSITIVE LOGITS
     snack
    1.19
     curfew
    1.10
     specials
    1.01
     snacks
    0.96
     festivities
    0.95
     stroll
    0.89
     vigil
    0.89
     arrival
    0.88
     entertainment
    0.86
     arrivals
    0.86
    Activations Density 0.105%

    No Known Activations